3D fingerprint expansion method and device

Abstract

The present disclosure relates to a 3D fingerprint expansion method and device, and relates to the field of fingerprint recognition. The specific implementation scheme includes: obtaining a three-dimensional point cloud of the finger, and obtaining an expanded fingerprint map by pre-processing the three-dimensional point cloud of the finger; obtaining a finger pressing fingerprint map, and estimating the finger posture when pressing based on the finger pressing fingerprint map and the expanded fingerprint map to obtain the finger spatial posture; correcting the three-dimensional point cloud based on the finger spatial posture, and thereby generating a 3D fingerprint expansion map under the corresponding posture. The present disclosure reduces the limitations of 3D fingerprint matching, prevents the finger matching model from not matching the finger shape, ensures that the 3D fingerprint expansion will not produce deformation, reduces the difference between the 3D fingerprint pressing posture and the finger pressing posture when pressing, and prevents fingerprint matching errors.

Description

Technical Field

[0001] The present disclosure relates to the field of fingerprint recognition, and in particular to a 3D fingerprint expansion method and device. Background Art

[0002] Fingerprints are very stable, easy to collect, and highly recognizable, making them one of the most widely used biometric features. Currently, the mainstream fingerprint collection method uses a contact sensor to acquire a 2D fingerprint image. However, the quality of these two-dimensional fingerprint images is affected by factors such as skin deformation and moisture. 3D fingerprint collection, on the other hand, uses a non-contact method to obtain fingerprints. The collected fingerprint data remains undistorted, is less affected by dryness or wetness, and is more hygienic.

[0003] Most expansion methods for 3D fingerprint collection assume that the finger is an axisymmetric parametric model and expand it accordingly. However, due to the irregular shape of the finger, these models cannot completely conform to the finger's shape, which will cause the fingerprint to deform during expansion. In addition, the deformation of the fingerprint is related to its pressing posture. Since the posture of the query fingerprint is unknown in advance, there may be a difference in pressing posture between the query fingerprint and the 3D fingerprint. When the 3D fingerprint is expanded during the registration stage, there will be a large deformation between the expanded fingerprint and the query fingerprint, which will lead to matching errors. Summary of the Invention

[0004] The present disclosure provides a 3D fingerprint expansion method and device.

[0005] According to a first aspect of an embodiment of the present disclosure, a 3D fingerprint expansion method is provided, comprising:

[0006] Obtain the three-dimensional point cloud of the finger, and obtain the unfolded fingerprint image by pre-processing the three-dimensional point cloud of the finger;

[0007] Obtain a fingerprint image of the finger pressed, estimate the finger posture when pressing based on the fingerprint image and the unfolded fingerprint image, and obtain the finger spatial posture;

[0008] Correcting the three-dimensional point cloud according to the finger spatial posture, and generating a 3D fingerprint expansion image under the corresponding posture according to the corrected three-dimensional point cloud;

[0009] According to a second aspect of an embodiment of the present disclosure, a 3D fingerprint expansion device is provided, comprising:

[0010] A processing module is used to obtain a three-dimensional point cloud of the finger and obtain an unfolded fingerprint image by pre-processing the three-dimensional point cloud of the finger;

[0011] The estimation module is used to obtain the fingerprint image of the finger pressed, estimate the finger posture when pressing the finger based on the fingerprint image and the unfolded fingerprint image, and obtain the finger spatial posture;

[0012] The correction module is used to correct the three-dimensional point cloud according to the finger spatial posture, and generate a 3D fingerprint expansion map under the corresponding posture according to the corrected three-dimensional point cloud.

[0013] According to a third aspect of the present disclosure, there is provided an electronic device, including:

[0014] at least one processor; and,

[0015] A memory communicatively coupled to at least one processor; wherein.

[0016] The memory stores instructions that can be executed by at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method of the first aspect.

[0017] According to a fourth aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable a computer to execute the method of the aforementioned first aspect.

[0018] The technical solutions provided by the embodiments of the present disclosure may have the following beneficial effects:

[0019] The present disclosure is divided into three stages as a whole, namely data collection, three-dimensional posture estimation and 3D fingerprint expansion under specific posture. In the first stage, the three-dimensional point cloud of the finger is collected, and the corresponding finger pressing fingerprint map is collected at the same time. In the second stage, based on the three-dimensional point cloud of the finger and the finger pressing fingerprint map collected in the first stage, the pressing posture of the finger when obtaining the pressing fingerprint is estimated. In the third stage, the finger point cloud posture is adjusted to make it the same as the finger posture estimated in the second stage, and the point cloud is expanded to obtain the 3D fingerprint expansion map corresponding to the pressing fingerprint. The limitations of 3D fingerprint matching are reduced, the finger matching model is prevented from not matching the finger shape, and the 3D fingerprint expansion is ensured not to be deformed. The difference between the 3D fingerprint pressing posture and the finger pressing posture when pressing is reduced, and fingerprint matching errors are prevented.

[0020] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0022] Figure 1 3D fingerprint expansion method provided by an embodiment of the present disclosure.

[0023] Figure 2 Schematic diagram of the spatial posture correction result provided by the embodiment of the present disclosure.

[0024] Figure 3 3D fingerprint expansion result diagram provided by an embodiment of the present disclosure.

[0025] Figure 4 FIG. 4 is a flow chart of a fingerprint expansion method provided by an embodiment of the present disclosure.

[0026] Figure 5 Schematic diagram of fingerprint visualization processing results provided by an embodiment of the present disclosure.

[0027] Figure 6 Schematic diagram of fingerprint expansion processing results provided by an embodiment of the present disclosure.

[0028] Figure 7 4 is a flow chart of a method for obtaining a finger spatial posture provided by an embodiment of the present disclosure.

[0029] Figure 8 It is a flow chart of the method for obtaining a 3D fingerprint expansion image provided by an embodiment of the present disclosure.

[0030] Figure 9 It is a structural block diagram of a 3D fingerprint expansion device provided by an embodiment of the present disclosure.

[0031] Figure 10 It is a structural block diagram of another 3D fingerprint expansion device provided by an embodiment of the present disclosure.

[0032] Figure 11 It is a structural block diagram of another 3D fingerprint expansion device provided by an embodiment of the present disclosure.

[0033] Figure 12 It is a structural block diagram of another 3D fingerprint expansion device provided by an embodiment of the present disclosure.

[0034] Figure 13 This is a structural block diagram of an electronic device for a 3D fingerprint expansion method provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0035] Exemplary embodiments will be described in detail herein, examples of which are illustrated in the accompanying drawings. In the following description, when referring to the drawings, like numbers in different figures represent like or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all possible embodiments consistent with the present invention. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present invention, as detailed in the appended claims.

[0036] It should be noted that fingerprint features are extremely stable, easy to collect, and highly recognizable, making them one of the most widely used biometrics. Currently, the mainstream fingerprint collection method uses a contact sensor to acquire a 2D fingerprint image. However, the quality of the 2D fingerprint image obtained with this method is affected by factors such as skin deformation and moisture. Compared to 2D fingerprints, 3D fingerprints use a non-contact method to acquire fingerprints. The collected finger data does not deform, is less affected by dryness or wetness, and is more hygienic. Since existing fingerprint databases primarily use 2D fingerprints and 2D fingerprint sensors are very popular, new 3D fingerprint sensors need to be compatible with 2D fingerprint sensors. Given that 3D fingerprint sensors are expensive and bulky, existing technology uses 3D sensors for registration and 2D sensors for recognition. To ensure compatibility, the registered 3D fingerprint is typically unfolded into a 2D fingerprint and then matched using conventional 2D fingerprint matching methods. There are many methods for 3D fingerprint unfolding. Most unfolding methods assume an axisymmetric parametric model of the finger and use this to unfold it. However, due to the irregular shape of the finger, these models cannot fully conform to the finger shape, which will cause additional deformation during unfolding. In addition, the deformation of the fingerprint is related to its pressing posture. Since the posture of the query fingerprint is unknown in advance, there may be differences in the pressing posture between the query fingerprint and the 3D fingerprint. When the 3D fingerprint is unfolded during the alignment stage, there will be a large deformation between the unfolded fingerprint and the query fingerprint, which will lead to mismatching.

[0037] To address the above issues, the present disclosure provides a 3D fingerprint expansion method and device. This disclosure can maintain the same pressing posture between the 3D finger and the query fingerprint before expansion, thereby reducing fingerprint deformation caused by the pressing posture and improving the compatibility between 3D fingerprints and 2D fingerprints, thereby enabling the use of 3D fingerprints in more application scenarios and improving the performance of fingerprint recognition algorithms in complex and difficult scenarios.

[0038] Figure 1 This is a flow chart of a 3D fingerprint expansion method provided by an embodiment of the present disclosure, as shown in FIG. Figure 1 As shown, the 3D fingerprint expansion method includes the following steps:

[0039] Step 101: Obtain a three-dimensional point cloud of the finger, and obtain an unfolded fingerprint image by pre-processing the three-dimensional point cloud of the finger.

[0040] Among them, the three-dimensional point cloud of the finger can be obtained through instruments such as a three-dimensional structured light scanner or RGBD (depth image camera).

[0041] It should be noted that the unfolded fingerprint image refers to the pattern obtained by flattening the three-dimensional point cloud of the finger on a plane.

[0042] Step 102: Obtain a fingerprint image of the finger when the finger is pressed, and estimate the finger posture when the finger is pressed based on the fingerprint image and the unfolded fingerprint image to obtain the finger spatial posture.

[0043] Among them, the finger pressed fingerprint image is the fingerprint image produced when the finger contacts the plane. The finger pressed fingerprint image is 2D fingerprint data. The fingerprint texture is relatively clear, but the contact area is small, easy to deform, and lacks three-dimensional shape information.

[0044] It should be noted that due to the modal differences between the 3D finger point cloud and the finger press fingerprint image, direct matching is not possible. Therefore, the 3D finger point cloud must be pre-processed to obtain an approximate unfolded fingerprint image. The finger spatial pose is then estimated based on the correspondence between the unfolded fingerprint image and the finger press fingerprint image. The finger spatial pose can be understood as the spatial pose of the finger relative to the 3D finger point cloud when pressing.

[0045] Step 103: Correct the three-dimensional point cloud according to the finger spatial posture, and generate a 3D fingerprint expansion image under the corresponding posture.

[0046] The correction results are as follows: Figure 2 As shown, Figure 2 The diagram of the spatial posture correction result is shown in Figure 2. The diagram of the 3D fingerprint expansion structure is shown in Figure 2. Figure 3 As shown, Figure 3 Schematic diagram of 3D fingerprint expansion results.

[0047] It should be noted that the spatial parameters of the finger spatial posture are corrected for the three-dimensional point cloud based on the comparison relationship between the finger pressed fingerprint image and the unfolded fingerprint image in step 102, in order to ensure that the finger spatial posture is consistent with the pressing posture of the pressed fingerprint. The correction relationship is:

[0048] V'=k(R3·V T +t3·A) T

[0049] Where V' is the point cloud after posture adjustment, R3, t3, k are the spatial posture parameters estimated in step 102, A is a 1×n all-one vector, and n is the number of points in the point cloud V.

[0050] The 3D fingerprint expansion method of the embodiment of the present disclosure is divided into three stages as a whole, namely data collection, three-dimensional posture estimation and 3D fingerprint expansion under a specific posture. In the first stage, the three-dimensional point cloud of the finger is collected, and the corresponding finger pressing fingerprint map is collected at the same time. In the second stage, based on the three-dimensional point cloud of the finger and the finger pressing fingerprint map collected in the first stage, the pressing posture of the finger when obtaining the pressing fingerprint is estimated. In the third stage, the finger point cloud posture is adjusted to make it the same as the finger posture estimated in the second stage, and the point cloud is expanded to obtain the 3D fingerprint expansion map corresponding to the pressing fingerprint. The limitations of 3D fingerprint matching are reduced, the finger matching model is prevented from not matching the finger shape, and the 3D fingerprint expansion is ensured to not be deformed. The difference between the 3D fingerprint pressing posture and the finger pressing posture when pressing is reduced, and fingerprint matching errors are prevented.

[0051] In one implementation, Figure 4 As shown, in order to ensure that the finger 3D point cloud can be matched with the finger press fingerprint image, the finger 3D point cloud needs to be pre-processed. Figure 4 As shown, the method for obtaining an expanded fingerprint image by pre-processing the three-dimensional point cloud of the finger includes the following steps:

[0052] Step 401, calculate the surface depth of each point in the three-dimensional point cloud of the finger, use the surface depth as the texture intensity value of the finger when pressing, and perform orthogonal projection on the three-dimensional point cloud of the finger according to the texture intensity value to obtain a visual fingerprint image, wherein the surface depth is normalized as the grayscale value of the visual image.

[0053] Among them, the visualization effects are as follows Figure 5 As shown, Figure 5 This is a schematic diagram of the fingerprint visualization processing results. Visualization is the theory, method and technology of using computer graphics and image processing technology to convert data into graphics or images and display them on the screen, and then perform interactive processing.

[0054] It should be noted that when a contact fingerprint collector collects a pressed fingerprint, the peaks of the finger's ridges are in contact with the plane more frequently, resulting in a darker color; whereas the valleys of the finger's ridges are largely free of contact with the plane, resulting in a lighter color. This disclosure simulates this property when visualizing a finger's three-dimensional point cloud. First, the surface depth of each point in the point cloud is estimated, and then the normalized surface depth is used as the grayscale value of the visualized image. For a point P in the point cloud V, the surface depth is calculated using its neighborhood point set, which is defined as:

[0055] X={x i |x i ∈Vand||x i -p|| <r},

[0056] The surface depth d of point P can be calculated based on the neighborhood point set X:

[0057] d=(pc) T n,

[0058] Where c is the geometric center of the neighborhood point set X, and n is the normal vector of the neighborhood point set X, which can be obtained by performing principal component analysis (PCA) on X. After calculating the surface depth of all points in the visual fingerprint image, it is normalized:

[0059]

[0060] where d max and d min are the maximum and minimum values ​​of all surface depths respectively, and the normalized surface depth d n As the grayscale value of the visual fingerprint.

[0061] Step 402: Expand the visualized fingerprint image to obtain an expanded fingerprint image.

[0062] Among them, the unfolding effect of the unfolded fingerprint image is as follows Figure 6 As shown, Figure 6 This is a schematic diagram of the fingerprint expansion processing results.

[0063] It should be noted that since the visual fingerprint image is a three-dimensional object, it is necessary to unfold the visual fingerprint image cloud onto a plane when matching it with the pressed fingerprint. This disclosure uses the arc length between two points in the point visual fingerprint image as the coordinate length after unfolding. Let (x, y, z) be the point cloud coordinate system, and (u, v, 0) be the coordinate system of the unfolded fingerprint. The transformation relationship between these two coordinate systems on the coordinate axis u is defined as:

[0064]

[0065] Among them, the transformation relationship of the coordinate axis v is the same as that of u.

[0066] In the 3D fingerprint expansion method of the disclosed embodiment, in the step of obtaining an expanded fingerprint image from a 3D finger point cloud, the surface depth of each point in the 3D finger point cloud is calculated, the surface depth is approximated as the texture intensity value of the corresponding contact fingerprint, and an orthogonal projection is performed on the 3D finger point cloud to obtain a visual fingerprint image. The visual fingerprint image is then expanded to obtain an expanded fingerprint image. This prevents mismatches between the finger matching model and the finger shape, ensures that the 3D fingerprint expansion does not produce deformation, reduces the difference between the 3D fingerprint pressing posture and the finger pressing posture during pressing, and prevents fingerprint matching errors.

[0067] In one implementation, Figure 7As shown in , in order to obtain the spatial posture diagram of the finger, the finger posture when pressing can be estimated based on the finger pressing fingerprint diagram and the unfolded fingerprint diagram. Figure 7 As shown, the method for estimating the finger posture when pressing the finger based on the finger pressed fingerprint image and the unfolded fingerprint image to obtain the finger spatial posture includes the following steps:

[0068] Step 701: derive the two-dimensional minutiae of the finger press fingerprint image by calculation, and obtain the two-dimensional paired minutiae of the unfolded fingerprint image and the corresponding three-dimensional paired minutiae in the three-dimensional point cloud by calculation.

[0069] Paired minutiae (feature points) are points where the grayscale value of an image changes dramatically, or points with large curvature on an image edge (i.e., the intersection of two edges). Paired minutiae reflect the essential characteristics of an image and can identify the target object in the image. Image matching can be achieved by matching feature points.

[0070] Step 702: Minimize the distance error between the two-dimensional projection of the three-dimensional matching minutiae points in the unfolded fingerprint image and the two-dimensional minutiae points in the finger pressed fingerprint image through formula calculation to estimate the finger spatial posture.

[0071] It should be noted that when estimating spatial posture, the paired feature points between the unfolded fingerprint image obtained by visualizing and unfolding the three-dimensional point cloud of the finger and the finger press fingerprint image are first calculated. Many algorithms can be used to calculate the paired feature points, such as first using the software VeriFinger to calculate the image feature points and then matching them using the MCC feature descriptor. Since the unfolded fingerprint image is generated from the three-dimensional point cloud of the finger, when the paired minutiae points of the unfolded fingerprint image and the press fingerprint are obtained, the corresponding relationship between the two-dimensional minutiae points of the finger press fingerprint image and the three-dimensional paired minutiae points of the three-dimensional cloud image is also obtained. The present disclosure calculates a set of rigid transformations in three-dimensional space to minimize the distance error between the two-dimensional projection of the three-dimensional paired minutiae points of the three-dimensional point cloud and the two-dimensional minutiae points of the finger press fingerprint image. The projection relationship is:

[0072]

[0073] Where (x m ,y m ,z m ) is the three-dimensional coordinate of the detail point in the point cloud, (u m ,v m ) are the 2D projection coordinates of the minutiae point, k is the scaling factor, R3 is the 3×3 rotation matrix, and t3 is the 3×1 displacement matrix. By minimizing the difference in the 2D coordinates between the projection of the point cloud minutiae point and the minutiae point on the fingerprint, the spatial pose of the finger's 3D point cloud relative to the fingerprint can be estimated.

[0074] The 3D fingerprint expansion method of the disclosed embodiment first calculates the two-dimensional minutiae of the finger pressed fingerprint image and the three-dimensional matching minutiae of the three-dimensional point cloud. Based on the correspondence between the two-dimensional minutiae and the three-dimensional matching minutiae, the method calculates the posture that minimizes the distance error between the two-dimensional projection of the three-dimensional matching minutiae and the two-dimensional minutiae of the finger pressed fingerprint image, thereby estimating the finger spatial posture. This allows the finger spatial posture to be more consistent with the actual situation, ensures the accuracy of fingerprint recognition, reduces the limitations of 3D fingerprint matching, prevents the finger matching model from mismatching the finger shape, ensures that the 3D fingerprint expansion will not produce deformation, reduces the difference between the 3D fingerprint pressing posture and the finger pressing posture during pressing, and prevents fingerprint matching errors.

[0075] In one implementation, Figure 8 As shown in , in order to obtain a 3D fingerprint expansion diagram, the finger spatial posture can be visualized and expanded. Figure 8 As shown, the method for obtaining a 3D fingerprint expansion image according to the corrected finger spatial posture includes the following steps:

[0076] Step 801 , performing posture correction on the three-dimensional point cloud using the estimated finger spatial posture, and visualizing and unfolding the posture-corrected three-dimensional point cloud to obtain a 3D fingerprint image having the same finger posture as that during the pressing operation.

[0077] It should be noted that the finger point cloud posture is adjusted by correction to be the same as the finger posture estimated in the second stage. According to the visualization and expansion methods given in steps 401 and 402, a 3D fingerprint expansion image with the same pressing posture as the pressed fingerprint is obtained.

[0078] Step 802 : cropping the 3D fingerprint image according to the fingerprint area when the finger is pressed to obtain a 3D fingerprint expansion image.

[0079] The 3D fingerprint expansion method of the embodiment of the present disclosure, after obtaining the spatial posture of the finger when pressing the fingerprint, corrects the three-dimensional point cloud according to the estimated spatial posture of the finger, makes it the same as the pressing posture of the fingerprint, corrects the posture of the three-dimensional point cloud according to the spatial posture of the finger under the posture, and visualizes and expands the three-dimensional point cloud. Finally, the 3D fingerprint expansion diagram is obtained by cropping. The accuracy of fingerprint matching is further guaranteed by correction, and the compatibility between 3D fingerprints and 2D fingerprints is improved by expansion and cropping. The limitations of 3D fingerprint matching are reduced, the mismatch between the finger matching model and the finger shape is prevented, the 3D fingerprint expansion is guaranteed not to be deformed, the difference between the pressing posture of the 3D fingerprint and the pressing posture of the finger when pressing is reduced, and fingerprint matching errors are prevented.

[0080] To implement the above embodiments, the present disclosure also proposes a 3D fingerprint unfolding device.

[0081] Figure 9 This is a structural block diagram of a 3D fingerprint expansion device provided in an embodiment of the present disclosure, such as Figure 9 As shown, the 3D fingerprint expansion device may include: a processing module 910, an estimation module 920, and a correction module 930.

[0082] The processing module 910 is used to obtain a three-dimensional point cloud of the finger, and obtain an expanded fingerprint image by pre-processing the three-dimensional point cloud of the finger.

[0083] The estimation module 920 is used to obtain a finger pressing fingerprint image, estimate the finger posture when pressing based on the finger pressing fingerprint image and the unfolded fingerprint image, and obtain the finger spatial posture.

[0084] The correction module 930 is used to correct the three-dimensional point cloud (3D fingerprint posture) according to the finger spatial posture, and generate a 3D fingerprint expansion map under the corresponding posture based on the corrected three-dimensional point cloud.

[0085] In some embodiments of the present application, Figure 10 As shown, Figure 10 1 is a structural block diagram of a 3D fingerprint expansion device according to another embodiment of the present disclosure. The processing module 1010 in the 3D fingerprint expansion device includes a calculation unit 1011 and an expansion unit 1012.

[0086] The calculation unit 1011 is used to calculate the surface depth of each point in the three-dimensional point cloud of the finger, perform orthogonal projection on the three-dimensional point cloud of the finger, and obtain a visual fingerprint image, wherein the surface depth is normalized as the grayscale value of the visual image.

[0087] The expansion unit 1012 is used to expand the visual fingerprint image to obtain an expanded fingerprint image.

[0088] in, Figure 10 Medium 1010-1030 and Figure 9 910-930 have the same function and structure.

[0089] In some embodiments of the present application, Figure 11 As shown, Figure 11 1 is a structural block diagram of a 3D fingerprint expansion device according to another embodiment of the present disclosure. In the 3D fingerprint expansion device, an estimation module 1120 includes a minutiae unit 1121 and an estimation unit 1122 .

[0090] The minutiae unit 1121 is used to calculate the two-dimensional minutiae of the finger press fingerprint image, and calculate the two-dimensional paired minutiae points of the unfolded fingerprint image and the corresponding three-dimensional paired minutiae points in the three-dimensional point cloud.

[0091] The estimation unit 1122 is used to minimize the distance error between the two-dimensional projection of the three-dimensional matching minutiae points in the expanded fingerprint image and the two-dimensional minutiae points in the finger pressed fingerprint image through formula calculation, so as to estimate the spatial posture of the finger when pressing the fingerprint.

[0092] in, Figure 11 1110-1130 and Figure 10 1010-1030 have the same function and structure.

[0093] In some embodiments of the present application, Figure 12 As shown, Figure 12 3D fingerprint expansion device according to another embodiment of the present disclosure, wherein the correction module 1230 includes: a processing unit 1231 and a cropping unit 1232.

[0094] The processing unit 1231 is used to perform posture correction on the three-dimensional point cloud based on the estimated finger spatial posture, and to visualize and expand the posture-corrected three-dimensional point cloud to obtain a 3D fingerprint image with the same finger posture as when pressing.

[0095] The cropping unit 1232 is used to crop the 3D fingerprint image according to the fingerprint area when the finger is pressed to obtain a 3D fingerprint expansion image.

[0096] in, Figure 12 Medium 1210-1230 and Figure 11 1110-1130 have the same function and structure.

[0097] The 3D fingerprint expansion device of the embodiment of the present disclosure is divided into three stages as a whole, namely data acquisition, three-dimensional posture estimation and 3D fingerprint expansion under a specific posture. In the first stage, the three-dimensional point cloud of the finger is collected, and the corresponding finger pressing fingerprint map is collected at the same time. In the second stage, based on the three-dimensional point cloud of the finger and the finger pressing fingerprint map collected in the first stage, the pressing posture of the finger when obtaining the pressing fingerprint is estimated. In the third stage, the finger point cloud posture is adjusted to make it the same as the finger posture estimated in the second stage, and the point cloud is expanded to obtain a 3D fingerprint expansion map corresponding to the pressing fingerprint. The limitations of 3D fingerprint matching are reduced, the finger matching model is prevented from not matching the finger shape, and the 3D fingerprint expansion is ensured to not be deformed. The difference between the 3D fingerprint pressing posture and the finger pressing posture when pressing is reduced, and fingerprint matching errors are prevented.

[0098] like Figure 13, is a block diagram of an electronic device for implementing a 3D fingerprint unfolding method according to an embodiment of the present disclosure. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are provided for example only and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0099] like Figure 13 As shown, the electronic device includes: one or more processors 1301, a memory 1302, and interfaces for connecting various components, including a high-speed interface and a low-speed interface. The various components are connected to each other using different buses and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the electronic device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as a display device coupled to the interface). In other embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple electronic devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 13 A processor 1301 is taken as an example.

[0100] Memory 1302 is a non-transitory computer-readable storage medium provided in the present disclosure. The memory stores instructions executable by at least one processor, causing the at least one processor to perform the 3D fingerprint expansion method provided in the present disclosure. The non-transitory computer-readable storage medium of the present disclosure stores computer instructions for causing a computer to perform the 3D fingerprint expansion method provided in the present disclosure.

[0101] The memory 1302 is a non-transient computer-readable storage medium that can be used to store non-transient software programs, non-transient computer executable programs and modules, such as the program instructions / modules corresponding to the 3D fingerprint expansion method in the embodiment of the present disclosure (for example, the attached Figure 10 The processor 1301 executes the non-transient software programs, instructions, and modules stored in the memory 1302 to execute various functional applications and data processing of the server, thereby implementing the 3D fingerprint expansion method in the above method embodiment.

[0102] The memory 1302 may include a program storage area and a data storage area. The program storage area may store an operating system and applications required for at least one function; the data storage area may store data created based on the use of the electronic device used to implement the 3D fingerprint deployment method. Furthermore, the memory 1302 may include high-speed random access memory and non-transient memory, such as at least one disk storage device, flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory 1302 may optionally include a memory remotely located relative to the processor 1301. These remote memories may be connected to the electronic device for intelligent dialogue via a network. Examples of the aforementioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0103] The electronic device for implementing the 3D fingerprint expansion method may further include: an input device 1303 and an output device 1304. The processor 1301, the memory 1302, the input device 1303 and the output device 1304 may be connected via a bus or other means. Figure 13 The bus connection is taken as an example.

[0104] The input device 1303 can receive input digital or character information, and generate key signal input related to user settings and function control of the electronic device of the intelligent dialogue, such as input devices such as a touch screen, a keypad, a mouse, a trackpad, a touch pad, an indicator stick, one or more mouse buttons, a trackball, a joystick, etc. The output device 1304 may include a display device, an auxiliary lighting device (e.g., an LED), and a tactile feedback device (e.g., a vibration motor). The display device may include, but is not limited to, a liquid crystal display (LCD), a light emitting diode (LED) display, and a plasma display. In some embodiments, the display device may be a touch screen.

[0105] Various implementations of the systems and techniques described herein can be realized in digital electronic circuit systems, integrated circuit systems, dedicated ASICs (application specific integrated circuits), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0106] These computer programs (also referred to as programs, software, software applications, or code) include machine instructions for a programmable processor and can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. As used herein, the terms "machine-readable medium" and "computer-readable medium" refer to any computer program product, apparatus, and / or device (e.g., a magnetic disk, an optical disk, a memory, a programmable logic device (PLD)) for providing machine instructions and / or data to a programmable processor, including a machine-readable medium that receives machine instructions as a machine-readable signal. The term "machine-readable signal" refers to any signal for providing machine instructions and / or data to a programmable processor.

[0107] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0108] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), the Internet, and a blockchain network.

[0109] A computer system may include a client and a server. The client and server are generally remote from each other and typically interact via a communication network. This client-server relationship is established by computer programs running on the respective computers, establishing a client-server relationship. The server may be a cloud server, also known as a cloud computing server or cloud host, a host product within the cloud computing service ecosystem that addresses the management difficulties and limited scalability of traditional physical hosts and VPS services ("Virtual Private Servers" or simply "VPS"). The server may also be a server in a distributed system or a server integrated with blockchain.

[0110] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this application can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved. This is not a limitation herein.

Claims

1. A 3D fingerprint expansion method, characterized in that: include: Acquire a three-dimensional point cloud of the finger, and obtain an unfolded fingerprint image by pre-processing the three-dimensional point cloud of the finger; Obtaining a finger pressed fingerprint image, estimating the finger posture when pressing based on the finger pressed fingerprint image and the unfolded fingerprint image, and obtaining the finger spatial posture; Correcting the three-dimensional point cloud according to the finger spatial posture, and generating a 3D fingerprint expansion image under the corresponding posture according to the corrected three-dimensional point cloud; The method of obtaining an expanded fingerprint image by pre-processing the three-dimensional point cloud of the finger includes: Calculate the surface depth of each point in the three-dimensional point cloud of the finger, use the surface depth as the texture intensity value of the finger when pressing, and perform orthogonal projection on the three-dimensional point cloud of the finger according to the texture intensity value to obtain a visual fingerprint image, wherein the surface depth is normalized as the grayscale value of the visual image; wherein, for a point in the point cloud V , calculate the surface depth using its neighborhood point set, the neighborhood point set X is defined as: Calculate the point based on the neighborhood point set X Surface depth d: Where c is the geometric center of the neighborhood point set X, and n is the normal vector of the neighborhood point set X, which is obtained by performing principal component analysis on X; The visual fingerprint image is expanded to obtain an expanded fingerprint image; wherein the arc length between two points of the point visual fingerprint image is used as the coordinate length after expansion, and is the point cloud coordinate system, To expand the coordinate system of the fingerprint, the transformation relationship between the two coordinate systems on the coordinate axis u is defined as: Among them, the transformation relationship of the coordinate axis v is the same as that of u.

2. The method according to claim 1, characterized in that The step of estimating the finger posture during pressing based on the finger pressed fingerprint image and the unfolded fingerprint image to obtain the finger spatial posture includes: Determine the two-dimensional minutiae of the finger pressed fingerprint image by calculation, and determine the two-dimensional paired minutiae of the unfolded fingerprint image and the corresponding three-dimensional paired minutiae in the three-dimensional point cloud by calculation; The distance error between the two-dimensional projection of the three-dimensional matching minutiae point in the expanded fingerprint image and the two-dimensional minutiae point in the finger pressed fingerprint image is minimized by formula calculation to estimate the finger spatial posture.

3. The method according to claim 1, characterized in that The correcting the three-dimensional point cloud according to the finger spatial posture, and generating a 3D fingerprint expansion image under the corresponding posture according to the corrected three-dimensional point cloud, includes: Performing posture correction on the three-dimensional point cloud based on the estimated finger spatial posture, and visualizing and expanding the posture-corrected three-dimensional point cloud to obtain a 3D fingerprint image with the same finger posture as when the finger was pressed; The 3D fingerprint image is cropped according to the fingerprint area when the finger is pressed to obtain the 3D fingerprint expansion image.

4. A 3D fingerprint unfolding device, comprising: A processing module, configured to obtain a three-dimensional point cloud of a finger and obtain an expanded fingerprint image by pre-processing the three-dimensional point cloud of the finger; An estimation module is used to obtain a finger pressing fingerprint image, estimate the finger posture when pressing based on the finger pressing fingerprint image and the expanded fingerprint image, and obtain the finger spatial posture; A correction module is used to correct the three-dimensional point cloud according to the spatial posture of the finger, and generate a 3D fingerprint expansion image under the corresponding posture according to the corrected three-dimensional point cloud; The processing module is specifically used for: The calculation unit is used to calculate the surface depth of each point in the three-dimensional point cloud of the finger, use the surface depth as the texture intensity value of the finger when pressing, and perform orthogonal projection on the three-dimensional point cloud of the finger according to the texture intensity value to obtain a visual fingerprint image, wherein the surface depth is normalized as the grayscale value of the visual image; wherein, for a certain point in the point cloud V , calculate the surface depth using its neighborhood point set, the neighborhood point set X is defined as: Calculate the point based on the neighborhood point set X Surface depth d: Where c is the geometric center of the neighborhood point set X, and n is the normal vector of the neighborhood point set X, which is obtained by performing principal component analysis on X; The expansion unit is used to expand the visual fingerprint image to obtain an expanded fingerprint image; wherein the arc length between two points of the point visual fingerprint image is used as the coordinate length after expansion, and is the point cloud coordinate system, To expand the coordinate system of the fingerprint, the transformation relationship between the two coordinate systems on the coordinate axis u is defined as: Among them, the transformation relationship of the coordinate axis v is the same as that of u.

5. The device according to claim 4, characterized in that The estimation module is specifically used for: a minutiae unit, configured to calculate the two-dimensional minutiae of the finger pressed fingerprint image, and calculate the two-dimensional paired minutiae of the unfolded fingerprint image and the corresponding three-dimensional paired minutiae in the three-dimensional point cloud; The estimation unit is used to minimize the distance error between the two-dimensional projection of the three-dimensional matching minutiae in the expanded fingerprint image and the two-dimensional minutiae in the finger pressed fingerprint image through formula calculation, so as to estimate the spatial posture of the finger when the fingerprint is pressed.

6. The device according to claim 4, characterized in that The correction module is specifically used for: a processing unit that performs posture correction on the three-dimensional point cloud based on the estimated finger spatial posture, and visualizes and expands the posture-corrected three-dimensional point cloud to obtain a 3D fingerprint image that is consistent with the finger posture during the pressing operation; The cropping unit is used to crop the 3D fingerprint image according to the fingerprint area when the finger is pressed to obtain the 3D fingerprint expansion image.

7. An electronic device, characterized in that: include: at least one processor; as well as, a memory communicatively coupled to the at least one processor; wherein: The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 3.

8. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1 to 3.

Images