Biological secret key generation method and storage medium
The fingerprint image of the fingertip is collected through an optical coherence tomography system, the internal fingerprint is extracted and converted into grayscale image, solving the problem of biometric abuse and template vulnerability, and achieving high-security information encryption.
Patent Information
- Application Number
- CN202310412305.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-04-18
- Publication Date
- 2025-07-18
AI Technical Summary
The abuse of existing human biometrics leads to reduced security, and the vulnerability of double random phase templates.
The fingerprint image of the fingertip is collected through an optical coherence tomography system, the internal fingerprint is extracted, the coordinates of the center point are obtained and the central area is selected. The upper and lower boundary thickness of the fingerprint epidermis is extracted using a convolutional neural network, and converted into a linear image with a preset grayscale value.
It improves the security of information encryption, increases the complexity of encryption structure, and provides a reference for new image or information encryption technologies.
Smart Images
Figure CN120340071A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of biometric key technologies, and particularly to a method for generating a biometric key and a storage medium. Background Art
[0002] Due to the unique biometric characteristics of each human body, such as fingerprints, faces, voices, etc., the biometric characteristics of the human body are widely used as keys in image or information encryption to improve the security of the system. However, the abuse of the biometric characteristics of the human body has led to a reduction in security. In addition, double random phase masks are widely used as keys in optical image encryption technology. However, due to the linear nature of double random phase masks, they are vulnerable to attacks. Therefore, there is an urgent need to develop a new type of key with high security and not easily attacked. Summary of the Invention
[0003] In view of the above problems, this application provides a method for generating a biometric key and a storage medium, which solves the problem of reduced security caused by the abuse of the biometric characteristics of the existing human body.
[0004] To achieve the above object, the inventor provides a method for generating a biometric key, including:
[0005] Collecting a fingertip fingerprint image through an optical coherence tomography system;
[0006] Extracting the internal fingerprint in the fingertip fingerprint image;
[0007] Obtaining the coordinates of the center point of the internal fingerprint, and selecting the central area of the internal fingerprint according to the center point coordinates;
[0008] According to the central area of the internal fingerprint, extracting the thickness of the upper and lower boundaries of the fingerprint epidermis layer through a convolutional neural network;
[0009] Converting the extracted thickness of the upper and lower boundaries of the fingerprint epidermis layer into a linear image with a preset gray value.
[0010] In some embodiments, the step of "extracting the internal fingerprint in the fingertip fingerprint image" specifically includes the following steps:
[0011] Using a convolutional neural network and interpolation method to obtain the image within the envelope curve of the local boundary maximum and minimum values of the fingertip skin epidermis layer and the epidermis-dermis junction in the fingertip fingerprint image, and obtaining the internal fingerprint through the maximum intensity projection algorithm.
[0012] In some embodiments, the step of "selecting the central area of the internal fingerprint according to the center point coordinates" specifically includes the following steps:
[0013] Taking a distance of a preset number of pixel points along the upper, lower, left, and right edges with the center point coordinates as the origin to form a square area with a preset pixel size as the central area.
[0014] In some embodiments, the following steps are further included:
[0015] Perform non-linear stretching on the pixel values of each pixel point in the obtained non-linear image to obtain a non-linear image.
[0016] In some embodiments, the following steps are further included:
[0017] Verify and analyze the randomness parameters of the obtained linear image and non-linear image. If the verification and analysis pass, then use the obtained linear image and non-linear image as biometric keys.
[0018] Another technical solution is also provided. A storage medium stores a computer program. When the computer program is run by a processor, the following steps are executed:
[0019] Collect a fingertip fingerprint image through an optical coherence tomography system;
[0020] Extract the internal fingerprint in the fingertip fingerprint image;
[0021] Obtain the central point coordinates of the internal fingerprint, and select the central area of the internal fingerprint according to the central point coordinates;
[0022] According to the central area of the internal fingerprint, extract the thickness of the upper and lower boundaries of the fingerprint epidermis layer through a convolutional neural network;
[0023] Convert the extracted thickness of the upper and lower boundaries of the fingerprint epidermis layer into a linear image with a preset gray value.
[0024] In some embodiments, the step of "extracting the internal fingerprint in the fingertip fingerprint image" specifically includes the following steps:
[0025] Use a convolutional neural network and interpolation method to obtain the image within the envelope curve of the local boundary maximum and minimum values of the fingertip skin epidermis layer and the epidermis-dermis junction in the fingertip fingerprint image, and obtain the internal fingerprint through the maximum intensity projection algorithm.
[0026] In some embodiments, the step of "selecting the central area of the internal fingerprint according to the central point coordinates" specifically includes the following steps:
[0027] Take a distance of a preset number of pixel points along the upper, lower, left, and right edges with the central point coordinates as the origin to form a square area with a preset pixel size as the central area.
[0028] In some embodiments, the following steps are further included:
[0029] Perform non-linear stretching on the pixel values of each pixel point in the obtained non-linear image to obtain a non-linear image.
[0030] In some embodiments, the following steps are further included:
[0031] Verify and analyze the randomness parameters of the acquired linear image and non-linear image. If the verification and analysis pass, use the acquired linear image and non-linear image as biological keys.
[0032] Different from the prior art, in the above technical solution, a fingertip fingerprint image is acquired by an optical coherence tomography system, and then the internal fingerprint is extracted according to the fingertip fingerprint image. The central point coordinates of the internal fingerprint are obtained, and the central region of the internal fingerprint is selected according to the central point coordinates. The thickness of the upper and lower boundaries of the fingerprint epidermis layer is extracted according to the central region of the internal fingerprint through a convolutional neural network, and then the thickness of the upper and lower boundaries of the fingerprint epidermis layer extracted is converted into a linear image with a preset gray value. Using the linear image of the three-dimensional epidermis layer thickness guided by the central region of the internal fingerprint of the fingertip skin based on the optical coherence tomography system as a new biological feature key greatly improves the security of information encryption, increases the complexity of the encryption structure, and provides a reference for new image or information encryption technologies.
[0033] The above relevant description of the invention content is only an overview of the technical solution of this application. In order to enable those of ordinary skill in the art to more clearly understand the technical solution of this application, and then can be implemented according to the content recorded in the text of the specification and the drawings, and in order to make the above objects, other objects, features and advantages of this application more easily understood, the following is described in conjunction with the specific implementation manners and drawings of this application. BRIEF DESCRIPTION OF THE DRAWINGS
[0034] The drawings are only used to illustrate the principles, implementation manners, applications, features and effects of the specific implementation manners of this application and other related contents, and should not be regarded as a limitation to this application.
[0035] In the drawings of the specification:
[0036] Figure 1 It is a schematic flowchart of one of the methods for generating biological keys described in the specific implementation manner;
[0037] Figure 2 It is a schematic flowchart of another method for generating biological keys described in the specific implementation manner;
[0038] Figure 3 It is a schematic diagram of one of the images of the envelope line region at the epidermis-dermis junction of the OCT fingertip skin described in the specific implementation manner;
[0039] Figure 4 It is a schematic diagram of one of the internal fingerprint images described in the specific implementation manner;
[0040] Figure 5It is a schematic diagram of the central region image of the internal fingerprint described in the specific implementation manner;
[0041] Figure 6 It is a schematic diagram of the envelope line region image of the epidermis-dermis junction corresponding to the central region of the internal fingerprint described in the specific implementation manner;
[0042] Figure 7 It is a schematic diagram of the upper and lower boundary images of the fingertip skin epidermis layer (the white area is the epidermis layer, and the black area is the background) described in the specific implementation manner;
[0043] Figure 8 It is a schematic diagram of the upper and lower boundary images of the fingertip skin epidermis layer corresponding to the central region of the internal fingerprint described in the specific implementation manner (the white area is the epidermis layer, and the black area is the background);
[0044] Figure 9 It is a schematic diagram of the linear thickness map guided by the central region of the internal fingerprint described in the specific implementation manner;
[0045] Figure 10 It is a schematic diagram of the non-linear thickness map guided by the central region of the internal fingerprint described in the specific implementation manner;
[0046] Figure 11 It is a schematic diagram of the gray histogram of the linear thickness map described in the specific implementation manner;
[0047] Figure 12 It is a schematic diagram of the gray histogram of the non-linear thickness map described in the specific implementation manner;
[0048] Figure 13 It is a schematic diagram of the adjacent pixel intensity map of the linear thickness map (from left to right are the horizontal, vertical, and diagonal directions in sequence) described in the specific implementation manner;
[0049] Figure 14 It is a schematic diagram of the adjacent pixel intensity map of the non-linear thickness map (from left to right are the horizontal, vertical, and diagonal directions in sequence) described in the specific implementation manner;
[0050] Figure 15 It is a schematic diagram of the average correlation coefficient and image entropy of adjacent pixels in the linear and non-linear thickness maps described in the specific implementation manner.
[0051] Figure 16 It is a schematic structural diagram of the storage medium described in the specific implementation manner.
[0052] The descriptions of the reference numerals involved in the above-mentioned respective drawings are as follows:
[0053] 210. Storage medium,
[0054] 220. Processor Detailed implementation manners
[0055] To describe in detail the possible application scenarios, technical principles, implementable specific solutions, achievable objectives and effects, etc. of the present application, the following will be described in detail in combination with the listed specific examples and with reference to the accompanying drawings. The embodiments described herein are only used to more clearly illustrate the technical solutions of the present application, and thus are only examples and cannot be used to limit the protection scope of the present application.
[0056] As used herein, the mention of "embodiment" means that the specific features, structures or characteristics described in connection with the embodiment may be included in at least one embodiment of the present application. The term "embodiment" appearing in various positions in the specification does not necessarily refer to the same embodiment, nor does it particularly limit its independence or relevance to other embodiments. In principle, in the present application, as long as there is no technical contradiction or conflict, the technical features mentioned in each embodiment can be combined in any way to form corresponding implementable technical solutions.
[0057] Unless otherwise defined, the meanings of the technical terms used herein are the same as those commonly understood by those skilled in the technical field to which the present application belongs; the use of the relevant terms herein is only for describing specific embodiments and is not intended to limit the present application.
[0058] In the description of the present application, the phrase "and / or" is an expression used to describe the logical relationship between objects, indicating that three relationships may exist. For example, A and / or B means: there is A, there is B, and there is both A and B at the same time. In addition, the character " / " in this article generally represents an "or" logical relationship between the associated objects before and after.
[0059] In the present application, terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual quantity, primary or secondary, or order relationship between these entities or operations.
[0060] Without more limitations, in the present application, the expressions such as "including", "comprising", "having" or other similar expressions used in the statements are intended to cover non-exclusive inclusion. These expressions do not exclude that there may be additional elements in the process, method or product including the said elements, so that the process, method or product including a series of elements may not only include those defined elements, but also include other elements not explicitly listed, or also include elements inherent to this process, method or product.
[0061] Similar to the understanding in the "Examination Guidelines", in this application, expressions such as "greater than", "less than", "exceeding", etc. are understood not to include the recited number; expressions such as "above", "below", "within", etc. are understood to include the recited number. In addition, in the description of the embodiments of this application, the meaning of "multiple" is two or more (including two), and similar expressions related to "many", such as "multiple groups", "multiple times", etc., are understood in this way unless otherwise clearly and specifically defined.
[0062] In the description of the embodiments of this application, the spatially related expressions used, such as "center", "longitudinal", "lateral", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "perpendicular", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", "axial", "radial", "circumferential", etc., the indicated orientation or positional relationship is based on the orientation or positional relationship shown in the specific embodiment or the drawings, and is only for the convenience of describing the specific embodiments of this application or for the reader to understand, rather than indicating or implying that the device or component referred to must have a specific position, a specific orientation, or be constructed or operated in a specific orientation, and therefore should not be construed as a limitation on the embodiments of this application.
[0063] Unless otherwise clearly specified or limited, in the description of the embodiments of this application, the terms such as "installed", "connected", "connected", "fixed", "set", etc. should be understood in a broad sense. For example, the "connection" can be a fixed connection, a detachable connection, or an integral setting; it can be a mechanical connection, an electrical connection, or a communication connection; it can be directly connected, or indirectly connected through an intermediate medium; it can be the communication inside two components or the interaction relationship between two components. For those skilled in the art to which this application belongs, the specific meanings of the above terms in the embodiments of this application can be understood according to specific circumstances.
[0064] Please refer to Figure 1 , this embodiment provides a method for generating a biological key, including:
[0065] Step S110: Collect a fingertip fingerprint image through an optical coherence tomography system;
[0066] Step S120: Extract the internal fingerprint in the fingertip fingerprint image;
[0067] Step S130: Obtain the coordinates of the center point of the internal fingerprint, and select the central area of the internal fingerprint according to the center point coordinates;
[0068] Step S140: According to the central area of the internal fingerprint, extract the thickness of the upper and lower boundaries of the fingerprint epidermis layer through a convolutional neural network;
[0069] Step S150: Convert the thickness of the upper and lower boundaries of the extracted fingerprint epidermal layer into a linear image of a preset gray value.
[0070] Use an optical coherence tomography system to acquire a fingertip fingerprint image, then extract the internal fingerprint according to the fingertip fingerprint image, obtain the center point coordinates of the internal fingerprint, and select the central region of the internal fingerprint according to the center point coordinates. Extract the thickness of the upper and lower boundaries of the fingerprint epidermal layer according to the central region of the internal fingerprint, and then convert the thickness of the extracted upper and lower boundaries of the fingerprint epidermal layer into a linear image of a preset gray value. The internal fingerprint of the finger is located at the papillary junction within the range of 220 - 550 μm from the fingertip skin surface, and has the same topography as the surface fingerprint. Optical coherence tomography (OCT) is a non-invasive imaging technology that can be used for the acquisition and reconstruction of internal fingerprints under the finger surface. Therefore, the features of the three-dimensional fingertip skin based on OCT have potential advantages in high-security information encryption. Using a linear image of the three-dimensional epidermal layer thickness guided by the central region of the internal fingerprint of the fingertip skin based on an optical coherence tomography system as a new biometric key greatly improves the security of information encryption, increases the complexity of the encryption structure, and provides a reference for new image or information encryption technologies.
[0071] In some embodiments, the step of "extracting the internal fingerprint in the fingertip fingerprint image" specifically includes the following steps:
[0072] Use a convolutional neural network and interpolation method to obtain the image within the envelope curve of the local boundary maximum and minimum values of the fingertip skin epidermal layer and the epidermal-dermal junction in the fingertip fingerprint image, and obtain the internal fingerprint through the maximum intensity projection algorithm.
[0073] The convolutional neural network includes two paths of upsampling and downsampling. In obtaining the internal fingerprint, identify the ridge and valley positions of the epidermal-dermal junction obtained through the convolutional neural network, calculate the local boundary maximum and minimum values to judge the ridge top and ridge valley, use the ridge line and valley line boundaries to construct an envelope curve through interpolation to determine the ridge line region, and combine the ridge line parts of each column in 400 images with a pixel size of 345 * 248 for maximum intensity projection to obtain an internal fingerprint image with a pixel size of 345 * 400.
[0074] In some embodiments, the step of "selecting the central region of the internal fingerprint according to the center point coordinates" specifically includes the following steps:
[0075] Take a distance of a preset number of pixel points along the upper, lower, left, and right edges with the center point coordinates as the origin to form a square region of a preset pixel size as the central region.
[0076] Among them, the central point coordinates of the internal fingerprint can be located manually or by image recognition. After locating the central point coordinates of the internal fingerprint, a square area with a pixel size of 101*101 is formed by taking 50 pixel points along the upper, lower, left, and right edges with the central coordinate point as the origin. The ridge line part of each column in 101 images with a pixel size of 101*248 is selected for maximum intensity projection to verify the accuracy of the selected area.
[0077] In some embodiments, the step of "extracting the thickness of the upper and lower boundaries of the fingerprint epidermis layer through a convolutional neural network according to the central area of the internal fingerprint" specifically includes the following steps:
[0078] Using the central area located in the internal fingerprint, 101 images of the upper and lower boundaries of the fingertip skin epidermis layer with a pixel size of 101*248 corresponding thereto are selected. The upper and lower boundaries of the fingertip skin epidermis layer are determined by segmentation through a convolutional neural network. For each image, the thickness of the upper and lower boundaries of the fingertip skin epidermis layer is statistically calculated column by column.
[0079] In some embodiments, the step of "converting the thickness of the upper and lower boundaries of the extracted fingerprint epidermis layer into a linear image of a preset gray value" includes the following steps:
[0080] The thickness of the upper and lower boundaries of the fingertip skin epidermis layer obtained by statistics is saved as a numpy array matrix with a size of 101*101 and converted into a linear image with gray values of 0-255.
[0081] In some embodiments, the following steps are further included:
[0082] The pixel value of each pixel point in the obtained non-linear image is subjected to non-linear stretching to obtain a non-linear image.
[0083] Then, the pixel value of each point in the linear image is subjected to non-linear stretching to obtain a non-linear image. The two are called the linear and non-linear images of the three-dimensional epidermis layer thickness guided by the internal fingerprint.
[0084] In some embodiments, the following steps are further included:
[0085] The randomness parameters of the obtained linear image and non-linear image are verified and analyzed. If the verification and analysis pass, the obtained linear image and non-linear image are used as biological keys.
[0086] The three randomness parameters of the linear and non-linear images of the three-dimensional epidermis layer thickness guided by the internal fingerprint are analyzed, including the gray histogram, adjacent pixel correlation, and image entropy, proving that the two are very close to random gray images, with high randomness and no information about the plaintext image carried, and can be used as keys.
[0087] Such asFigure 2 As shown in the figure, a biological key generation method generates a new biological key based on the internal fingerprint of the fingertip skin OCT image, including: using the maximum intensity projection algorithm to obtain the internal fingerprint, locating the central area of the internal fingerprint, extracting the upper and lower boundary thicknesses of the fingerprint epidermis layer through a convolutional neural network, converting them into linear and non-linear images with gray values from 0 to 255, and analyzing the randomness of the two keys to prove that using them for image or information encryption is more secure and reliable.
[0088] In some embodiments, a key based on the internal fingerprint-guided three-dimensional epidermis layer thickness is proposed for image or information encryption. The key generation algorithm includes three steps. First, apply a convolutional neural network to segment the upper and lower boundaries of the epidermis layer in the OCT fingertip skin image, and use the maximum intensity projection algorithm to extract the internal fingerprint at the epidermis-dermis junction of the fingertip skin. Second, by locating a part of the area in the internal fingerprint, calculate the thickness of the upper and lower boundaries of the fingertip skin epidermis layer. Finally, convert it into two biological keys, namely a linear thickness map and a non-linear thickness map. The present invention can encrypt the epidermis thickness of the fingertip skin as an important biometric information, and the internal fingerprint-guided epidermis thickness from the OCT image is a potential information encryption method.
[0089] In some embodiments, a biological key generation method includes the following steps:
[0090] Identify the positions of the ridges and valleys at the epidermis-dermis junction obtained through a convolutional neural network, calculate the local boundary maximum and minimum values to judge the ridge tops and valleys, and use the ridge line and valley line boundaries to construct an envelope curve through interpolation to determine the ridge line area, obtaining an envelope line area image of the OCT fingertip skin epidermis-dermis junction, as Figure 3 shown. By performing maximum intensity projection on 400 envelope line area images of the epidermis-dermis junction with a pixel size of 345*248, an internal fingerprint image with a pixel size of 345*400 is obtained, as Figure 4 shown.
[0091] As Figure 4 shown, manually locate the central coordinate point of the internal fingerprint image using a circle, and take a distance of 50 pixel points along the upper, lower, left, and right edges with the central coordinate point as the origin to form a red square area with a pixel size of 101*101. The located central area of the internal fingerprint is as Figure 5 shown. The envelope line area image of the epidermis-dermis junction corresponding to the central area of the internal fingerprint is as Figure 6 shown
[0092] The upper and lower boundaries of the fingertip skin epidermis layer are determined by segmentation through a convolutional neural network, as Figure 7As shown. Using the central region located in the internal fingerprint, 101 upper and lower boundary images of the fingertip skin epidermis layer with a pixel size of 101*248 corresponding to it are selected. For each image, the number of white region pixel points is statistically counted column by column, as Figure 8 shown.
[0093] The thickness of the upper and lower boundaries of the fingertip skin epidermis layer obtained by statistics is saved as a numpy array matrix of size 101*101, and it is converted into a linear image with gray values of 0-255, as Figure 9 shown. In addition, the pixel value of each point in this linear image is non-linearly stretched to obtain a non-linear image, as Figure 10 shown.
[0094] The gray histogram of the linear thickness map is as Figure 11 shown, and the gray histogram of the non-linear thickness map is as Figure 12 shown. It can be seen from the figure that except for 65, the pixel values of both are roughly evenly distributed between 0 and 255, which may be affected by human biological characteristics.
[0095] In a random image, the degree of correlation between adjacent pixels is reflected by the correlation of adjacent pixels, and its definition is:
[0096]
[0097] where J is the number of adjacent pixel pairs randomly selected in the image. Here, J = 3000, and (x i , y i ) is the intensity value of the adjacent pixel pair. For a gray image with a gray level range of 256, the calculation method of entropy is:
[0098]
[0099] where P(G i ) is the probability of each gray value appearing in the image.
[0100] The adjacent pixel intensity maps of the linear thickness map in the horizontal, vertical, and diagonal directions are as Figure 13 shown, and the adjacent pixel intensity maps of the non-linear thickness map in the horizontal, vertical, and diagonal directions are as Figure 14 shown. The average correlation coefficients of adjacent pixels and the image entropy in the three directions of the linear and non-linear thickness maps are as Figure 15 shown. It can be seen from the figure that the average correlation coefficients of adjacent pixels in the three directions of the linear and non-linear thickness maps are all close to 0, and the image entropy is all close to 8, with a relatively high randomness.
[0101] Therefore, the linear and non-linear images of the three-dimensional epidermal layer thickness guided by internal fingerprints are more suitable as a new biometric key for image or information encryption, with high security.
[0102] Please refer to Figure 16 , in another embodiment, a storage medium 210 stores a computer program, and when the computer program is run by a processor 220, the following steps are executed:
[0103] Collect a fingertip fingerprint image through an optical coherence tomography system;
[0104] Extract the internal fingerprint in the fingertip fingerprint image;
[0105] Obtain the coordinates of the center point of the internal fingerprint, and select the central area of the internal fingerprint according to the center point coordinates;
[0106] According to the central area of the internal fingerprint, extract the thickness of the upper and lower boundaries of the fingerprint epidermal layer through a convolutional neural network;
[0107] Convert the extracted thickness of the upper and lower boundaries of the fingerprint epidermal layer into a linear image with a preset gray value.
[0108] Collect a fingertip fingerprint image through an optical coherence tomography system, then extract the internal fingerprint according to the fingertip fingerprint image, obtain the coordinates of the center point of the internal fingerprint, select the central area of the internal fingerprint according to the center point coordinates, extract the thickness of the upper and lower boundaries of the fingerprint epidermal layer through a convolutional neural network according to the central area of the internal fingerprint, and then convert the extracted thickness of the upper and lower boundaries of the fingerprint epidermal layer into a linear image with a preset gray value. The internal fingerprint of the finger is located at the papillary junction within the range of 220 - 550 μm on the fingertip skin surface, and has the same topography as the surface fingerprint. Optical coherence tomography (OCT) is a non-invasive imaging technique that can be used for the acquisition and reconstruction of internal fingerprints under the finger surface. Therefore, the features of the three-dimensional fingertip skin based on OCT have potential advantages in high-security information encryption. Using the linear image of the three-dimensional epidermal layer thickness guided by the central area of the internal fingerprint of the fingertip skin based on an optical coherence tomography system as a new biometric key greatly improves the security of information encryption, increases the complexity of the encryption structure, and provides a reference for new image or information encryption technologies.
[0109] In some embodiments, the step of "extracting the internal fingerprint in the fingertip fingerprint image" specifically includes the following steps:
[0110] Use a convolutional neural network and interpolation method to obtain the image within the envelope curve of the local boundary maximum and minimum values of the fingertip skin epidermal layer and the epidermal-dermal junction in the fingertip fingerprint image, and obtain the internal fingerprint through the maximum intensity projection algorithm.
[0111] The convolutional neural network contains two paths of upsampling and downsampling. In obtaining the internal fingerprint, the positions of the ridges and valleys at the epidermal-dermal junction obtained by recognition through the convolutional neural network are used to calculate the local boundary maximum and minimum values to judge the ridge tops and ridge valleys. The envelope curve is constructed by the interpolation method using the ridge line and valley line boundaries to determine the ridge line region. The maximum intensity projection is performed on each column of the ridge line part in 400 images with a pixel size of 345*248, and an internal fingerprint image with a pixel size of 345*400 is obtained.
[0112] In some embodiments, the step of "selecting the central region of the internal fingerprint according to the central point coordinates" specifically includes the following steps:
[0113] By taking the distance of a preset number of pixel points along the upper, lower, left, and right edges with the central point coordinates as the origin, a square region with a preset pixel size is formed as the central region.
[0114] Among them, the central point coordinates of the internal fingerprint can be located manually or by image recognition. After the central point coordinates of the internal fingerprint are located, the distance of 50 pixel points is taken along the upper, lower, left, and right edges with the central coordinate point as the origin, a square region with a pixel size of 101*101 is formed, and the maximum intensity projection is performed on each column of the ridge line part in 101 images with a pixel size of 101*248 to verify the accuracy of the selected region.
[0115] In some embodiments, the step of "extracting the thickness of the upper and lower boundaries of the fingerprint epidermal layer through the convolutional neural network according to the central region of the internal fingerprint" specifically includes the following steps:
[0116] Using the central region located in the internal fingerprint, 101 upper and lower boundary images of the fingertip skin epidermal layer with a pixel size of 101*248 corresponding thereto are selected. The upper and lower boundaries of the fingertip skin epidermal layer are determined by segmentation through the convolutional neural network, and the thickness of the upper and lower boundaries of the fingertip skin epidermal layer is statistically calculated for each image by column.
[0117] In some embodiments, the step of "converting the thickness of the upper and lower boundaries of the extracted fingerprint epidermal layer into a linear image with a preset gray value" includes the following steps:
[0118] The thickness of the upper and lower boundaries of the fingertip skin epidermal layer obtained by statistics is saved as a numpy array matrix with a size of 101*101, and it is converted into a linear image with a gray value of 0-255.
[0119] In some embodiments, the following steps are further included:
[0120] The pixel value of each pixel point in the obtained non-linear image is non-linearly stretched to obtain a non-linear image.
[0121] Next, perform non-linear stretching on the pixel values of each point in the linear image to obtain a non-linear image. These two are referred to as the linear and non-linear images of the three-dimensional epidermal layer thickness guided by internal fingerprints.
[0122] In some embodiments, the following steps are further included:
[0123] Verify and analyze the randomness parameters of the obtained linear image and non-linear image. If the verification and analysis pass, then use the obtained linear image and non-linear image as biological keys.
[0124] Analyze the three randomness parameters of the linear and non-linear images of the three-dimensional epidermal layer thickness guided by internal fingerprints, including the gray histogram, adjacent pixel correlation, and image entropy. Prove that the two are very close to random gray images, with high randomness and no information about the plaintext image carried, and can be used as keys.
[0125] Finally, it should be noted that although the above embodiments have been described in the text and drawings of the specification of this application, the patent protection scope of this application cannot be limited thereby. Any equivalent structure or equivalent process substitution or modification made based on the essential concept of this application, using the content recorded in the text and drawings of the specification of this application, as well as directly or indirectly implementing the technical solutions of the above embodiments in other related technical fields, etc., are all included in the patent protection scope of this application.
Claims
1. A biological key generation method, characterized in that, Including: Collecting fingertip fingerprint images through an optical coherence tomography system; Extracting the internal fingerprint in the fingertip fingerprint image; Obtaining the central point coordinates of the internal fingerprint and selecting the central region of the internal fingerprint according to the central point coordinates; Extracting the thickness of the upper and lower boundaries of the fingerprint epidermal layer through a convolutional neural network according to the central region of the internal fingerprint; Converting the extracted thickness of the upper and lower boundaries of the fingerprint epidermal layer into a linear image with a preset gray value.
2. The biological key generation method according to claim 1, characterized in that, The step of "extracting the internal fingerprint in the fingertip fingerprint image" specifically includes the following steps: Using a convolutional neural network and interpolation method to obtain the image within the envelope curve of the local boundary maximum and minimum values of the fingertip skin epidermal layer and the epidermal-dermal junction in the fingertip fingerprint image, and obtaining the internal fingerprint through the maximum intensity projection algorithm.
3. The biological key generation method according to claim 1, characterized in that, The step of "selecting the central region of the internal fingerprint according to the central point coordinates" specifically includes the following steps: Forming a square region with a preset pixel size as the central region by taking the distances of a preset number of pixel points along the upper, lower, left, and right edges with the central point coordinates as the origin.
4. The biological key generation method according to claim 1, characterized in that It also includes the following steps: Performing non-linear stretching on the pixel value of each pixel point in the obtained non-linear image to obtain a non-linear image.
5. The biological key generation method according to claim 4, wherein, It also includes the following steps: Verifying and analyzing the randomness parameters of the obtained linear image and non-linear image. If the verification and analysis pass, the obtained linear image and non-linear image are used as biological keys.
6. A storage medium storing a computer program, characterized in that, When the computer program is run by a processor, it performs the following steps: Collecting fingertip fingerprint images through an optical coherence tomography system; Extracting the internal fingerprint in the fingertip fingerprint image; Obtaining the central point coordinates of the internal fingerprint and selecting the central region of the internal fingerprint according to the central point coordinates; Extracting the thickness of the upper and lower boundaries of the fingerprint epidermal layer through a convolutional neural network according to the central region of the internal fingerprint; Converting the extracted thickness of the upper and lower boundaries of the fingerprint epidermal layer into a linear image with a preset gray value.
7. The storage medium according to claim 6, characterized in that, The step of "extracting the internal fingerprint in the fingertip fingerprint image" specifically includes the following steps: Using a convolutional neural network and interpolation method to obtain the image within the envelope curve of the local boundary maximum and minimum values of the fingertip skin epidermal layer and the epidermal-dermal junction in the fingertip fingerprint image, and obtaining the internal fingerprint through the maximum intensity projection algorithm.
8. The storage medium according to claim 6, wherein The step of "selecting the central region of the internal fingerprint according to the central point coordinates" specifically includes the following steps: Forming a square region with a preset pixel size as the central region by taking the distances of a preset number of pixel points along the upper, lower, left, and right edges with the central point coordinates as the origin.
9. The storage medium according to claim 6, wherein It also includes the following steps: Performing non-linear stretching on the pixel value of each pixel point in the obtained non-linear image to obtain a non-linear image.
10. The storage medium according to claim 9, wherein It also includes the following steps: Verifying and analyzing the randomness parameters of the obtained linear image and non-linear image. If the verification and analysis pass, the obtained linear image and non-linear image are used as biological keys.