A control method, system, device and medium of an intelligent lock

Abstract

The application relates to the technical field of intelligent locks and discloses an intelligent lock control method, system, device and medium, the method comprising the following steps: acquiring a palm vein image of a user to be identified and a preset grating image, the preset grating image being a two-dimensional array containing multiple rectangular grating frames; extracting vein cross points of the palm vein image to obtain key detection points; mapping the key detection points to the preset grating image to obtain a first image; judging whether the first image matches a preset first unlocking image; when the first image matches the preset first unlocking image, optimizing the preset first unlocking image based on the palm vein image and the key detection points to obtain a second image; judging whether the second image matches a preset second unlocking image; and when the second image matches the preset second unlocking image, controlling the intelligent lock to be unlocked. The application can improve the speed and accuracy of palm vein identification, so that the intelligent lock can be quickly, accurately and safely controlled.

Description

Technical Field

[0001] This invention relates to the field of smart lock technology, and specifically to a control method, system, device, and medium for a smart lock. Background Technology

[0002] Smart locks are locks that differ from traditional mechanical locks, offering greater intelligence in user identification, security, and management. Smart locks are the locking mechanism in access control systems. Currently, some smart locks utilize fingerprint recognition technology to unlock doors. However, because fingerprint recognition only requires identifying one finger, the verification information is relatively limited, reducing the security of the smart lock. Furthermore, after unlocking the door with fingerprint information, some smart locks lack protective mechanisms, exposing the fingerprint information and making it vulnerable to copying, further compromising security.

[0003] To enhance the security of smart locks, palm vein recognition has been applied. Palm vein recognition is a technology that uses the vein characteristics of the palm for secure identification. It identifies the veins throughout the entire palm, making the verification information more complex, preventing information leakage, and making it difficult to copy, thus significantly improving the security of smart locks. However, existing smart locks still suffer from drawbacks in palm vein recognition, such as slow response speed, complex recognition process, and poor recognition results. Summary of the Invention

[0004] In view of this, the present invention provides a control method, system, device and medium for smart locks to solve the problems of slow response speed, complex recognition process and poor recognition effect of existing smart locks based on palm vein recognition, which make it difficult to meet the needs of smart lock use.

[0005] In a first aspect, the present invention provides a control method for a smart lock, the method comprising:

[0006] Acquire the palm vein image and the preset raster image of the user to be identified. The preset raster image is a two-dimensional array containing multiple rectangular raster frames.

[0007] Extract the vein intersections from the palm vein image to obtain key detection points;

[0008] The key detection points are mapped onto a preset raster image to obtain the first image;

[0009] Determine whether the first image matches the preset first unlock image;

[0010] When the first image is matched with the preset first unlock image, the preset first unlock image is optimized based on the palm vein image and key detection points to obtain the second image;

[0011] Determine whether the second image matches the preset second unlock image;

[0012] When the second image matches the preset second unlock image, the smart lock is unlocked.

[0013] The control method for the smart lock of the present invention extracts the vein intersections of the palm vein image and sets two recognition matching methods, which can significantly improve the palm vein recognition processing and response time, ensure the accuracy and efficiency of recognition, and realize fast, accurate and secure control of the smart lock.

[0014] In one alternative implementation, before extracting the vein intersections from the palm vein image, the control method for the smart lock further includes:

[0015] Extracting the region of interest from a palm vein image;

[0016] Calculate the mean image of the region of interest;

[0017] The difference image is obtained by subtracting the region of interest image from the mean image;

[0018] Determine histogram equalization and curvature images based on the difference images;

[0019] The histogram equalization image and the curvature image are fused to obtain the updated palm vein image.

[0020] This invention removes irrelevant redundant data and enhances image features by extracting regions of interest, subtracting images, and fusing images from palm vein images. At the same time, it can reduce the amount of data processing and speed up the subsequent recognition process.

[0021] In one optional implementation, determining whether the first image matches a preset first unlock image includes:

[0022] Calculate the first similarity between the first image and the preset first unlock image;

[0023] Determine whether the first similarity score is greater than a first preset threshold;

[0024] If the first similarity is greater than the first preset threshold, then the first image is determined to match the preset first unlock image;

[0025] If the first similarity is not greater than the first preset threshold, then it is determined that the first image does not match the preset first unlock image.

[0026] The present invention can ensure the accuracy of palm vein recognition by determining whether the first image matches the preset first unlock image.

[0027] In one optional implementation, a second image is obtained by optimizing a preset first unlocking image based on a palm vein image and key detection points, including:

[0028] The palm vein image is fused with the preset first unlock image to obtain the recognition image;

[0029] The recognized image is input into a preset optimization model for image optimization, resulting in an optimized image;

[0030] Image sampling is performed on the optimized image based on key detection points to obtain a second image.

[0031] This invention optimizes the preset first unlocking image based on palm vein images and key detection points, which can enrich the detailed features of the image and help improve the speed and accuracy of subsequent palm vein recognition, enabling fast, accurate and secure control of smart locks.

[0032] In one optional implementation, determining whether the second image matches a preset second unlock image includes:

[0033] Calculate the second similarity between the second image and the preset second unlock image;

[0034] Determine whether the second similarity is greater than the second preset threshold;

[0035] If the second similarity is greater than the second preset threshold, then the second image is determined to match the preset second unlock image;

[0036] If the second similarity is not greater than the second preset threshold, then it is determined that the second image does not match the preset second unlock image.

[0037] The present invention can ensure the accuracy of palm vein recognition and improve the security of smart locks by judging whether the second image matches the preset second unlock image.

[0038] In one optional implementation, the process of setting a preset first unlock image and a preset second unlock image includes:

[0039] Responding to the command password of the user to be identified, and verifying whether the command password is the same as the preset initial password;

[0040] After the command password is the same as the preset initial password, the unlocked palm vein image of the user to be identified is acquired, and the unlocked palm vein image is preprocessed to obtain the processed image;

[0041] The processed image is input into a preset optimization model to obtain the unlocked image, and the sparsity of the unlocked image is calculated.

[0042] Key unlock detection points are extracted from unlock images based on sparsity and vein intersections;

[0043] Construct a preset first unlock image based on key unlock detection points;

[0044] Based on key unlock detection points, refined unlock nodes are obtained by isochronous sampling from the unlock palm vein image and the unlock image, and a preset second unlock image is constructed based on the refined unlock nodes and key unlock detection points.

[0045] The present invention, by using a pre-set first unlock image and a pre-set second unlock image, can take into account individual differences in palm veins and improve the accuracy of palm vein recognition.

[0046] In an optional implementation, when the first image does not match a preset first unlock image, or when the second image does not match a preset second unlock image, the control method of the smart lock further includes:

[0047] Control the smart lock to maintain the locked state, and / or perform early warning processing.

[0048] When the palm vein recognition results do not match, this invention designs corresponding control operations for the smart lock, which can improve the function of the smart lock and meet the actual use needs of the smart lock.

[0049] Secondly, the present invention provides a control system for a smart lock, the system comprising:

[0050] The acquisition module is used to acquire the palm vein image and the preset raster image of the user to be identified. The preset raster image is a two-dimensional array containing multiple rectangular raster frames.

[0051] The extraction module is used to extract the vein intersections in the palm vein image to obtain key detection points;

[0052] The mapping module is used to map key detection points onto a preset raster image to obtain a first image;

[0053] The first judgment module is used to determine whether the first image matches the preset first unlock image;

[0054] The optimization module is used to optimize the preset first unlock image based on the palm vein image and key detection points when the first image is matched with the preset first unlock image to obtain the second image;

[0055] The second judgment module is used to determine whether the second image matches the preset second unlock image;

[0056] The control module is used to control the smart lock to unlock when the second image matches the preset second unlocking image.

[0057] The control system of the smart lock of the present invention extracts the vein intersections of the palm vein image and sets two recognition matching methods, which can greatly improve the palm vein recognition processing and response time, ensure the accuracy and efficiency of recognition, and realize fast, accurate and secure control of the smart lock.

[0058] Thirdly, the present invention provides a computer device, comprising: a memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the computer instructions to perform a control method for a smart lock as described in the first aspect or any corresponding embodiment.

[0059] Fourthly, the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to execute a control method for a smart lock according to the first aspect or any corresponding embodiment described above. Attached Figure Description

[0060] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0061] Figure 1 This is a flowchart illustrating the control method of a smart lock according to an embodiment of the present invention;

[0062] Figure 2 This is a flowchart illustrating another control method for a smart lock according to an embodiment of the present invention;

[0063] Figure 3 This is a schematic diagram of the structure of a smart lock according to an embodiment of the present invention;

[0064] Figure 4 This is a flowchart illustrating another intelligent lock control method according to an embodiment of the present invention;

[0065] Figure 5 This is a structural block diagram of the control system of a smart lock according to an embodiment of the present invention;

[0066] Figure 6 This is a schematic diagram of the structure of a computer device according to an embodiment of the present invention. Detailed Implementation

[0067] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0068] This invention provides an embodiment of a control method for a smart lock. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0069] This embodiment provides a control method for a smart lock. Figure 1 This is a flowchart illustrating the control method of a smart lock according to an embodiment of the present invention, as shown below. Figure 1 As shown, the process includes the following steps:

[0070] Step S101: Obtain the palm vein image and the preset raster image of the user to be identified. The preset raster image is a two-dimensional array containing multiple rectangular raster frames.

[0071] It should be noted that palm veins are the faintly visible blue veins through the skin of the palm, encompassing all the venous systems within the palm area. The heme in the red blood cells of these veins is deoxygenated heme, which absorbs near-infrared radiation. Therefore, when near-infrared light shines on the palm, only the veins show a weak reflection, thus forming the palm vein image corresponding to the vein patterns. In this embodiment, the method of acquiring the palm vein image is not limited; it is obtained based on commonly used methods in the art, such as obtaining a clear palm vein image using infrared imaging technology, and is merely illustrative.

[0072] In this embodiment, a two-dimensional array is generated regularly using scan lines produced by a grating, i.e., a preset grating image is obtained. The specific values ​​of the two-dimensional array are adaptively adjusted based on actual needs.

[0073] Step S102: Extract the vein intersections from the palm vein image to obtain key detection points.

[0074] It should be noted that, due to the individual uniqueness of palm vein images, that is, each person's palm vein image is different, and different palm vein images of the same person are also different, this embodiment obtains the key feature points of the palm vein image, namely the vein intersection points, to make the palm vein recognition features more representative, which helps to reduce the curse of dimensionality and improve the efficiency and accuracy of subsequent palm vein recognition.

[0075] Step S103: Map the key detection points to a preset raster image to obtain the first image.

[0076] In this embodiment, the specific implementation method for mapping key detection points to a preset grating image is not limited, and can be adapted based on actual needs. For example, constructing an image containing key detection points and performing homography transformation on this image and the preset grating image to obtain a first image is only an example.

[0077] Step S104: Determine whether the first image matches the preset first unlock image.

[0078] It should be noted that the preset first unlocking image in this embodiment is a pre-set first unlocking matrix, which is pre-set and stored in the smart lock.

[0079] In step S105, when the first image is matched with the preset first unlock image, the preset first unlock image is optimized based on the palm vein image and key detection points to obtain the second image.

[0080] In this embodiment, the method of optimizing the preset first unlock image is not limited, and is adaptively selected based on actual needs. For example, optimizing the preset first unlock image using a pre-trained model is only an example.

[0081] Step S106: Determine whether the second image matches the preset second unlock image.

[0082] It should be noted that the preset second unlocking image in this embodiment is a pre-set second unlocking matrix, which is pre-set and stored in the smart lock.

[0083] Step S107: When the second image matches the preset second unlocking image, control the smart lock to unlock.

[0084] The control method for the smart lock in this embodiment of the invention extracts the vein intersections of the palm vein image and sets two recognition matching methods, which can significantly improve the palm vein recognition processing and response time, ensure the accuracy and efficiency of recognition, and realize fast, accurate and secure control of the smart lock.

[0085] This embodiment provides a control method for a smart lock. Figure 2 This is a flowchart illustrating another smart lock control method according to an embodiment of the present invention, as shown below. Figure 2 As shown, the process includes the following steps:

[0086] Step S201: Obtain the palm vein image and a preset raster image of the user to be identified. The preset raster image is a two-dimensional array containing multiple rectangular raster frames. For details, please refer to [link to details]. Figure 1 Step S101 of the illustrated embodiment will not be described again here.

[0087] It should be noted that this embodiment also includes preprocessing of the acquired raw palm vein image to ensure its quality. Specifically, the preprocessing includes:

[0088] Step A1: Extract the region of interest image from the palm vein image.

[0089] It should be noted that extracting the Region of Interest (ROI) from the original entire palm vein image for subsequent palm vein feature extraction and recognition can remove noise or other pixels that affect the recognition effect, retain richer image features, reduce the amount of data processing required for subsequent recognition, and speed up the recognition process.

[0090] In this embodiment, the specific method for determining the ROI is not limited, and the method is adaptively selected based on the accuracy requirements of the actual project. For example, the ROI can be obtained by solving the problem using common operators and functions in machine vision libraries or software such as OpenCV and Matlab; or the ROI can be extracted based on a fixed length, that is, using the centroid of the palm vein image as the center, setting a fixed length such as 100 pixels or 150 pixels as the side length or a fixed length of a preset shape for ROI extraction. This can ensure that the extracted ROI is within the palm and contains less interference. This is only an example for illustration.

[0091] Step A2: Calculate the mean image of the region of interest.

[0092] In this embodiment, the mean image is obtained using the mean function in OpenCV.

[0093] Step A3: Subtract the region of interest image from the mean image to obtain the difference image.

[0094] Step A4: Determine the histogram equalization image and curvature image based on the difference image.

[0095] It should be noted that histogram equalization enhances image contrast by stretching the range of pixel intensity distribution. The histogram equalized image in this embodiment can be obtained using the equalizeHist function in OpenCV; the curvature image can be obtained using the curvature filtering algorithm in OpenCV, which is only used as an example.

[0096] Step A5: Fuse the histogram equalization image and the curvature image to obtain the updated palm vein image.

[0097] The embodiments of the present invention can remove uninteresting redundant data and enhance image features by performing region of interest extraction, image subtraction, and image fusion on palm vein images; at the same time, it can also reduce the amount of data processing and speed up the subsequent recognition process.

[0098] Step S202: Extract the vein intersections from the palm vein image to obtain key detection points. For details, please refer to [link to relevant documentation]. Figure 1 Step S102 of the illustrated embodiment will not be described again here.

[0099] Step S203: Map the key detection points onto a preset raster image to obtain the first image. For details, please refer to [link to relevant documentation]. Figure 1 Step S103 of the illustrated embodiment will not be described again here.

[0100] Step S204: Determine whether the first image matches the preset first unlock image.

[0101] Specifically, step S204 includes:

[0102] Step B1: Calculate the first similarity between the first image and the preset first unlock image.

[0103] In this embodiment, the specific calculation method for the first similarity is not limited and can be adjusted adaptively based on actual needs. For example, the images can be converted into corresponding vector representations, and the similarity between the two images can be characterized by calculating the cosine distance between the vectors. This is only an example for illustration.

[0104] Step B2: Determine whether the first similarity is greater than the first preset threshold.

[0105] In this embodiment, the specific value of the first preset threshold is not limited, but is determined adaptively based on the actual project requirements. For example, the first preset threshold is 0.8, which is only for illustrative purposes.

[0106] Step B3: If the first similarity is greater than the first preset threshold, then the first image is determined to match the preset first unlock image.

[0107] Step B4: If the first similarity is not greater than the first preset threshold, then it is determined that the first image does not match the preset first unlock image.

[0108] The embodiments of the present invention can ensure the accuracy of palm vein recognition by determining whether the first image matches the preset first unlock image.

[0109] In step S205, when the first image is matched with the preset first unlock image, the preset first unlock image is optimized based on the palm vein image and key detection points to obtain the second image.

[0110] Specifically, step S205 includes:

[0111] Step S2051: The palm vein image is fused with the preset first unlock image to obtain the recognition image.

[0112] Step S2052: Input the recognized image into the preset optimization model for image optimization to obtain the optimized image.

[0113] It should be noted that the preset optimization model in this embodiment is a pre-trained palm vein recognition model. The specific type of palm vein recognition model is not limited here and can be adaptively adjusted based on actual needs. For example, palm vein recognition models include long short-term memory network models, recurrent neural network models, convolutional neural network models, etc., which are only used as examples.

[0114] Step S2053: Based on the key detection points, perform image sampling on the optimized image to obtain the second image.

[0115] The embodiments of the present invention optimize the preset first unlocking image based on palm vein images and key detection points, which can enrich the detailed features of the image and help improve the speed and accuracy of subsequent palm vein recognition, and achieve fast, accurate and secure control of smart locks.

[0116] Step S206: Determine whether the second image matches the preset second unlock image.

[0117] Specifically, step S204 includes:

[0118] Step C1: Calculate the second similarity between the second image and the preset second unlock image.

[0119] In this embodiment, the specific calculation method for the second similarity is not limited and can be adjusted adaptively based on actual needs. For example, the correlation between the histograms of two images can be calculated using the histogram algorithm in OpenCV, which is only used as an example.

[0120] Step C2: Determine whether the second similarity is greater than the second preset threshold.

[0121] In this embodiment, the specific value of the second preset threshold is not limited and is determined adaptively based on the actual project requirements. For example, the first preset threshold is 0.95, which is only for illustrative purposes. It should be noted that the specific values ​​of the first preset threshold and the second preset threshold in this embodiment can be the same or different, and are both adjusted adaptively based on actual needs. For example, in order to improve the accuracy of palm vein recognition, the value of the first preset threshold can be set to be less than the second preset threshold; in order to improve the speed of palm vein recognition, the value of the first preset threshold can be set to be equal to the second preset threshold.

[0122] Step C3: If the second similarity is greater than the second preset threshold, then the second image is determined to match the preset second unlock image.

[0123] Step C4: If the second similarity is not greater than the second preset threshold, then it is determined that the second image does not match the preset second unlock image.

[0124] Step S207: When the second image matches the preset second unlocking image, control the smart lock to unlock.

[0125] It should be noted that when the first image does not match the preset first unlocking image, or when the second image does not match the preset second unlocking image, the control method of the smart lock in this embodiment further includes: controlling the smart lock to maintain the locked state, and / or performing early warning processing. Specifically, the method of early warning processing is not limited here and can be adaptively adjusted based on actual needs. For example, the smart lock may perform an audible and visual alarm, which is only an example. This embodiment of the invention designs corresponding control operations for the smart lock when the palm vein recognition results do not match, which can improve the functionality of the smart lock and meet the actual usage needs of the smart lock.

[0126] In this embodiment, the preset first unlock image and the preset second unlock image can be preset by the authorized user of the smart lock and stored in the smart lock. The specific setting process includes:

[0127] Step D1: In response to the instruction password of the user to be identified, verify whether the instruction password is the same as the preset initial password.

[0128] In this embodiment, the instruction password refers to the digital password entered by the user on the smart lock; the preset initial password is a digital password that is pre-set and stored in the smart lock for verifying user information.

[0129] Step D2: After the instruction password is the same as the preset initial password, the unlocked palm vein image of the user to be identified is acquired, and the unlocked palm vein image is preprocessed to obtain the processed image.

[0130] In this embodiment, the specific method of preprocessing the unlocked palm vein image is not limited and can be adaptively adjusted based on actual needs. For example, extracting the region of interest, denoising the image, and adjusting the image angle are only illustrative examples.

[0131] Step D3: Input the processed image into the preset optimization model to obtain the unlocked image, and calculate the sparsity of the unlocked image.

[0132] In this embodiment, the sparsity of an image is used to measure the proportion of zero elements in the image to the total number of elements. It can be solved by the image sparsity processing function in machine vision software such as OpenCV and Matlab.

[0133] Step D4: Extract key unlock detection points from the unlock image based on sparsity and vein intersections.

[0134] Step D5: Construct a preset first unlock image based on key unlock detection points.

[0135] Step D6: Based on the key unlock detection points, perform equidistant sampling from the unlock palm vein image and the unlock image to obtain refined unlock nodes, and construct a preset second unlock image based on the refined unlock nodes and the key unlock detection points.

[0136] The embodiments of the present invention, by using a preset first unlock image and a preset second unlock image, can take into account individual differences in palm veins and improve the accuracy of palm vein recognition.

[0137] In one specific embodiment, Figure 3 This is a schematic diagram of the structure of a smart lock according to an embodiment of the present invention. Figure 3 It is understood that infrared imaging technology is integrated into the palm vein recognition area (i.e., palm vein recognition module) of the smart lock to obtain the corresponding palm vein image. In addition, a preset grating image and a first unlocking matrix and a second unlocking matrix are pre-set and stored in the smart lock, and the control method of the smart lock in this embodiment is integrated into the smart lock to realize the palm vein recognition of the user to be identified, and to realize precise control of the smart lock based on the recognition result.

[0138] Specifically, the process of setting the first unlock matrix and the second unlock matrix includes: responding to the received instruction password, verifying that the instruction password is the same as the preset initial password, and acquiring an unlock palm vein image through the palm vein recognition area; preprocessing the unlock palm vein image to obtain an intermediate processed image; inputting the intermediate processed image into a pre-trained palm vein recognition model to obtain an unlock node image, and calculating the sparsity of the unlock node distribution in the unlock node image; labeling the vein recognition box in the unlock node image according to the sparsity; setting the unlock nodes within the vein recognition box and at the vein intersections as key unlock detection points, and constructing the first unlock matrix from the key unlock detection points; performing equidistant sampling on the unlock nodes between adjacent key unlock detection points in the two images of the unlock palm vein image and the unlock node image to obtain refined unlock nodes, and constructing the second unlock matrix from the refined unlock nodes and the key unlock detection points.

[0139] This embodiment provides a control method for a smart lock. Figure 4 This is a flowchart illustrating another control method for a smart lock according to an embodiment of the present invention, as shown below. Figure 4 As shown, the process includes the following steps:

[0140] Step E1: Acquire palm vein images using the palm vein recognition module, and extract ROI images from the acquired palm vein images.

[0141] Step E2: Preprocess the ROI image to obtain intermediate image I, and extract the nodes at the vein crossings in intermediate image I to obtain key detection points.

[0142] Step E3: A two-dimensional array is generated regularly using the scan lines produced by the grating, and the key detection points are mapped onto the two-dimensional array to obtain a mapping matrix.

[0143] Step E4: Match the mapping matrix with the pre-stored first unlock matrix. If the match is successful, output the first unlock matrix; if the match fails, output a warning message.

[0144] Step E5: Overlay the first unlocking matrix with the intermediate processed image I to obtain the recognition region image. Input the recognition region image into the pre-trained palm vein recognition model to obtain the refinement node. Sample the refinement node according to the key detection point to obtain the sampled node.

[0145] Step E6: Generate a recognition node image based on the sampling node and key detection point. Match the recognition node image with the pre-stored second unlocking matrix. If the match is successful, output an unlocking command; if the match fails, output a warning message.

[0146] In this embodiment, after successfully obtaining the unlock command, the smart lock is unlocked; if the matching fails, the smart lock remains locked and a voice announcement is made that the verification failed.

[0147] In summary, the smart lock control method of this invention, by extracting the vein intersections of the palm vein image and setting two recognition matching methods, accelerates the palm vein recognition processing and response time, ensures the accuracy and efficiency of recognition, and achieves fast, accurate and secure control of the smart lock.

[0148] This embodiment also provides a control system for a smart lock, which is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, a "module" can be a combination of software and / or hardware that performs a predetermined function. Although the system described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0149] This invention provides a control system for a smart lock, such as... Figure 5 As shown, the system includes:

[0150] The acquisition module 501 is used to acquire the palm vein image and the preset raster image of the user to be identified. The preset raster image is a two-dimensional array containing multiple rectangular raster frames.

[0151] Extraction module 502 is used to extract the vein intersections in the palm vein image to obtain key detection points.

[0152] The mapping module 503 is used to map key detection points to a preset raster image to obtain a first image.

[0153] The first judgment module 504 is used to determine whether the first image matches the preset first unlock image.

[0154] The optimization module 505 is used to optimize the preset first unlock image based on the palm vein image and key detection points when the first image is matched with the preset first unlock image to obtain the second image.

[0155] The second judgment module 506 is used to determine whether the second image matches the preset second unlock image.

[0156] The control module 507 is used to control the smart lock to unlock when the second image matches the preset second unlocking image.

[0157] In some optional implementations, the first judgment module 504 includes: a first calculation submodule, a first judgment submodule, a first result submodule, and a second result submodule; wherein, the first calculation submodule is used to calculate a first similarity between the first image and a preset first unlock image; the first judgment submodule is used to determine whether the first similarity is greater than a first preset threshold; the first result submodule is used to determine that the first image matches the preset first unlock image if the first similarity is greater than the first preset threshold; and the second result submodule is used to determine that the first image does not match the preset first unlock image if the first similarity is not greater than the first preset threshold.

[0158] In some optional implementations, the optimization module 505 includes: a first optimization submodule, a second optimization submodule, and a third optimization submodule; wherein, the first optimization submodule is used to perform image fusion between the palm vein image and a preset first unlock image to obtain a recognition image; the second optimization submodule is used to input the recognition image into a preset optimization model for image optimization to obtain an optimized image; and the third optimization submodule is used to perform image sampling on the optimized image based on key detection points to obtain a second image.

[0159] In some optional implementations, the second determination module 506 includes: a second calculation submodule, a second determination submodule, a third result submodule, and a fourth result submodule; wherein, the second calculation submodule is used to calculate a second similarity between the second image and a preset second unlock image; the second determination submodule is used to determine whether the second similarity is greater than a second preset threshold; the third result submodule is used to determine that the second image matches the preset second unlock image if the second similarity is greater than the second preset threshold; and the fourth result submodule is used to determine that the second image does not match the preset second unlock image if the second similarity is not greater than the second preset threshold.

[0160] In some optional implementations, the second result submodule or the fourth result submodule may further include: a control unit for controlling the smart lock to maintain the locked state, and / or for performing early warning processing.

[0161] In some optional implementations, the system further includes: a preprocessing module for extracting a region of interest (ROI) image from a palm vein image; calculating a mean image of the ROI image; subtracting the ROI image from the mean image to obtain a difference image; determining a histogram equalization image and a curvature image based on the difference image; and fusing the histogram equalization image and the curvature image to obtain an updated palm vein image.

[0162] In some optional implementations, the system further includes: a setting module, configured to respond to the command password of the user to be identified and verify whether the command password is the same as the preset initial password; after the command password is the same as the preset initial password, to acquire an unlocked palm vein image of the user to be identified and to preprocess the unlocked palm vein image to obtain a processed image; to input the processed image into a preset optimization model to obtain an unlocked image and to calculate the sparsity of the unlocked image; to extract key unlocking detection points from the unlocked image based on the sparsity and vein intersections; to construct a preset first unlocked image based on the key unlocking detection points; to obtain refined unlocking nodes by isometric sampling from the unlocked palm vein image and the unlocked image based on the key unlocking detection points, and to construct a preset second unlocked image based on the refined unlocking nodes and the key unlocking detection points.

[0163] Further functional descriptions of the above modules are the same as those in the corresponding embodiments described above, and will not be repeated here.

[0164] In this embodiment, the control system of the smart lock is presented in the form of functional units. Here, a unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that execute one or more software or fixed programs, and / or other devices that can provide the above functions.

[0165] The control system of the smart lock in this embodiment of the invention extracts the vein intersections of the palm vein image and sets two recognition matching methods, which can greatly improve the palm vein recognition processing and response time, ensure the accuracy and efficiency of recognition, and realize fast, accurate and secure control of the smart lock.

[0166] This invention also provides a computer device; please refer to [link / reference]. Figure 6 , Figure 6 This is a schematic diagram of the structure of the computer device described above, provided in an optional embodiment of the present invention, as shown below. Figure 6 As shown, the computer device includes one or more processors 10, memory 20, and interfaces for connecting the components, including high-speed interfaces and low-speed interfaces. The components communicate with each other via different buses and can be mounted on a common motherboard or otherwise installed as needed. The processors can process instructions executed within the computer device, including instructions stored in or on memory to display graphical information of a GUI on external input / output devices (such as display devices coupled to the interfaces). In some alternative implementations, multiple processors and / or multiple buses can be used with multiple memories and multiple memory modules, if desired. Similarly, multiple computer devices can be connected, each providing some of the necessary operations (e.g., as a server array, a group of blade servers, or a multiprocessor system). Figure 6 Take a processor 10 as an example.

[0167] Processor 10 may be a central processing unit, a network processor, or a combination thereof. Processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The programmable logic device may be a complex programmable logic device (CAMP), a field-programmable gate array (FPGA), a general-purpose array logic (GDA), or any combination thereof.

[0168] The memory 20 stores instructions executable by at least one processor 10 to cause at least one processor 10 to perform the method shown in the above embodiments.

[0169] The memory 20 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the computer device. Furthermore, the memory 20 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some alternative embodiments, the memory 20 may optionally include memory remotely located relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0170] The memory 20 may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as flash memory, hard disk or solid-state drive; the memory 20 may also include a combination of the above types of memory.

[0171] The computer device also includes a communication interface 30 for the main control chip to communicate with other devices or communication networks.

[0172] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as recordable on a storage medium, or implemented as computer code originally stored on a remote storage medium or a non-transitory machine-readable storage medium and subsequently stored on a local storage medium after being downloaded via a network. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor main control chips, or programmable hardware include storage components capable of storing or receiving software or computer code. When the software or computer code is accessed and executed by the computer, processor, or hardware, the methods shown in the above embodiments are implemented.

[0173] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A control method for a smart lock, characterized in that, The method includes: Acquire a palm vein image and a preset grating image of the user to be identified, wherein the preset grating image is a two-dimensional array containing multiple rectangular grating frames; Extract the vein intersections from the palm vein image to obtain key detection points; The key detection points are mapped onto the preset raster image to obtain a first image; Determine whether the first image matches a preset first unlock image; When the first image is matched with the preset first unlock image, the preset first unlock image is optimized based on the palm vein image and the key detection points to obtain the second image; Determine whether the second image matches the preset second unlock image; When the second image matches the preset second unlocking image, the smart lock is controlled to unlock.

2. The control method for the smart lock according to claim 1, characterized in that, Before extracting the vein intersections from the palm vein image, the method further includes: Extract the region of interest image from the palm vein image; Calculate the mean image of the region of interest; The difference image is obtained by subtracting the region of interest image from the mean image; Based on the difference image, determine the histogram equalization image and the curvature image; The histogram equalization image and the curvature image are fused to obtain an updated palm vein image.

3. The control method for the smart lock according to claim 1, characterized in that, The step of determining whether the first image matches the preset first unlock image includes: Calculate the first similarity between the first image and the preset first unlock image; Determine whether the first similarity is greater than a first preset threshold; If the first similarity is greater than the first preset threshold, then the first image is determined to match the preset first unlock image; If the first similarity is not greater than the first preset threshold, then it is determined that the first image does not match the preset first unlock image.

4. The control method for the smart lock according to any one of claims 1 to 3, characterized in that, The optimization of the preset first unlocking image based on the palm vein image and the key detection points to obtain the second image includes: The palm vein image is fused with the preset first unlock image to obtain a recognition image; The recognized image is input into a preset optimization model for image optimization to obtain an optimized image; Based on the key detection points, the optimized image is sampled to obtain a second image.

5. The control method for the smart lock according to claim 4, characterized in that, The step of determining whether the second image matches the preset second unlock image includes: Calculate the second similarity between the second image and the preset second unlock image; Determine whether the second similarity is greater than a second preset threshold; If the second similarity is greater than the second preset threshold, then the second image is determined to match the preset second unlock image; If the second similarity is not greater than the second preset threshold, then it is determined that the second image does not match the preset second unlock image.

6. The control method for the smart lock according to claim 1, characterized in that, The process of setting the preset first unlock image and the preset second unlock image includes: In response to the instruction password of the user to be identified, the system verifies whether the instruction password is the same as the preset initial password. After the command password is the same as the preset initial password, the unlocked palm vein image of the user to be identified is acquired, and the unlocked palm vein image is preprocessed to obtain a processed image; The processed image is input into a preset optimization model to obtain an unlocked image, and the sparsity of the unlocked image is calculated. Key unlocking detection points are extracted from the unlocking image based on the sparsity and vein intersections. A preset first unlocking image is constructed based on the key unlocking detection points; Based on the key unlock detection points, refined unlock nodes are obtained by isochronous sampling from the unlock palm vein image and the unlock image, and a preset second unlock image is constructed based on the refined unlock nodes and the key unlock detection points.

7. The control method for the smart lock according to claim 3 or 5, characterized in that, When the first image does not match the preset first unlock image, or when the second image does not match the preset second unlock image, the method further includes: Control the smart lock to maintain the locked state, and / or perform early warning processing.

8. A control system for a smart lock, characterized in that, The system includes: The acquisition module is used to acquire the palm vein image and the preset grating image of the user to be identified. The preset grating image is a two-dimensional array containing multiple rectangular grating frames. The extraction module is used to extract the vein intersections in the palm vein image to obtain key detection points; The mapping module is used to map the key detection points to the preset raster image to obtain a first image; The first judgment module is used to determine whether the first image matches the preset first unlock image; An optimization module is used to optimize the preset first unlock image based on the palm vein image and the key detection points when the first image is matched with the preset first unlock image, so as to obtain a second image; The second judgment module is used to determine whether the second image matches the preset second unlock image; The control module is used to control the smart lock to unlock when the second image matches the preset second unlock image.

9. A computer device, characterized in that, The device includes a memory and a processor, which are communicatively connected to each other. The memory stores computer instructions, and the processor executes the computer instructions to perform the control method of the smart lock according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to execute the control method of the smart lock according to any one of claims 1 to 7.

Images