Fingerprint recognition method, device and computer readable storage medium

Abstract

The embodiment of the present invention discloses a fingerprint recognition method, which includes: collecting a fingerprint to be recognized, and obtaining depth information and image information of the fingerprint to be recognized; obtaining first fingerprint data based on the depth information and image information; and performing recognition processing on the fingerprint to be recognized based on the first fingerprint data. The embodiment of the present invention also discloses a fingerprint recognition device and a computer-readable storage medium.

Description

Technical Field

[0001] The present invention relates to the field of fingerprint recognition, and in particular to a fingerprint recognition method, device and computer-readable storage medium. Background Art

[0002] With the rapid development and maturity of mobile payment services, fingerprint recognition technology has become a standard feature of smartphones. Fingerprint recognition technology is a biometric technology that uses collected fingerprints for identity recognition. Fingerprint collection is the basis of fingerprint recognition technology, and collecting clear and accurate fingerprints is of great significance to fingerprint recognition.

[0003] Currently, fingerprint collection technologies include optical collection technology, semiconductor silicon collection technology and ultrasonic collection technology; among them, optical collection technology has higher requirements for fingers and has poor imaging capabilities for dry fingers, wet fingers and dirty fingers; semiconductor silicon collection technology is easily affected by environmental factors such as static electricity and cannot image wet fingers and dirty fingers; ultrasonic collection technology takes a long time to collect and requires special equipment for emitting ultrasonic waves, which will cause the problem of high collection costs.

[0004] Based on the above analysis, it can be seen that the existing fingerprint recognition technology cannot accurately identify special fingers such as wet fingers, dirty fingers, etc., and has strict requirements on the collection environment and high collection costs. Summary of the invention

[0005] To solve the existing technical problems, the embodiments of the present invention provide a fingerprint recognition method, device and computer-readable storage medium, which solve the problem that special fingers cannot be accurately recognized in the prior art, and reduce the environmental requirements and fingerprint collection costs during fingerprint recognition.

[0006] To achieve the above object, the technical solution of the embodiment of the present invention is implemented as follows:

[0007] In a first aspect, a fingerprint recognition method is provided, the method comprising:

[0008] Collecting a fingerprint to be identified, and obtaining depth information and image information of the fingerprint to be identified;

[0009] Based on the depth information and the image information, obtaining first fingerprint data;

[0010] Based on the first fingerprint data, identification processing is performed on the fingerprint to be identified.

[0011] In a second aspect, a fingerprint recognition device is provided, the fingerprint recognition device comprising at least: a processor and a storage medium configured to store executable instructions, wherein:

[0012] The processor is configured to execute stored executable instructions, the executable instructions comprising:

[0013] Collecting a fingerprint to be identified, and obtaining depth information and image information of the fingerprint to be identified;

[0014] Based on the depth information and the image information, obtaining first fingerprint data;

[0015] Based on the first fingerprint data, identification processing is performed on the fingerprint to be identified.

[0016] According to a third aspect, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are configured to execute the fingerprint recognition method provided in the first aspect.

[0017] The fingerprint recognition method, device and computer-readable storage medium provided by the embodiments of the present invention collect a fingerprint to be recognized, and obtain depth information and image information of the fingerprint to be recognized, and then obtain first fingerprint data based on the depth information and image information, and finally perform recognition processing on the fingerprint to be recognized based on the first fingerprint data; in this way, when collecting fingerprints, not only the image information of the fingerprint is obtained, but also the depth information of the fingerprint is obtained, and the first fingerprint data is obtained based on the depth information and image information, and then the first fingerprint with the depth information and image information is recognized and processed. In this way, the fingerprint to be recognized is recognized using information of two dimensions, namely, the depth information and the image information, so that the problem of inaccurate recognition of special fingers in the existing fingerprint recognition technology can be solved, and the recognition accuracy is improved. In addition, the fingerprint collection method for collecting depth information and image information has low requirements on the surrounding environment, thereby reducing the requirements on the environment and the collection cost. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 A schematic diagram of a fingerprint recognition method according to an embodiment of the present invention;

[0019] Figure 2 A schematic diagram of a flow chart of another fingerprint recognition method provided by an embodiment of the present invention;

[0020] Figure 3 A schematic diagram of a flow chart of another fingerprint recognition method provided by an embodiment of the present invention;

[0021] Figure 4 A schematic flow chart of a fingerprint recognition method is provided for another embodiment of the present invention;

[0022] Figure 5 A schematic diagram of the structure of a fingerprint recognition device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0023] To make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the specific technical solution of the invention will be further described in detail below in conjunction with the drawings in the embodiments of the present invention. The following embodiments are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0024] In order to clearly describe the technical solutions of the embodiments of the present invention, in the embodiments of the present invention, the words "first", "second", etc. are used to distinguish the same items or similar items with basically the same functions or effects. Those skilled in the art can understand that the words "first", "second", etc. do not limit the quantity and execution order.

[0025] It should be understood that the "embodiments of the present invention" or "the aforementioned embodiments" mentioned throughout the specification mean that specific features, structures or characteristics related to the embodiments are included in at least one embodiment of the present invention. Therefore, "in the embodiments of the present invention" or "in the aforementioned embodiments" appearing in various places throughout the specification do not necessarily refer to the same embodiment. In addition, these specific features, structures or characteristics can be combined in one or more embodiments in any suitable manner. It is understood that in various embodiments of the present invention, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention. The serial numbers of the above-mentioned embodiments of the present invention are for description only and do not represent the advantages and disadvantages of the embodiments.

[0026] The present invention provides a fingerprint recognition method. Figure 1 As shown, the method comprises the following steps:

[0027] Step 101: Collect a fingerprint to be identified, and obtain depth information and image information of the fingerprint to be identified.

[0028] Among them, step 101 collects the fingerprint to be identified, and obtains the depth information and image information of the fingerprint to be identified, which can be implemented by a fingerprint recognition device; the fingerprint recognition device is any type of device with a fingerprint recognition function, such as a smartphone, tablet computer, personal digital assistant (PDA), smart wearable device, access control device, attendance device, etc. with a fingerprint recognition function.

[0029] In other embodiments of the present invention, the image information may be information contained in the collected two-dimensional fingerprint image; for example, the image information may be the position information of each pixel point in the two-dimensional space coordinates of the two-dimensional fingerprint image. The depth information may be the distance information between the fingerprint collecting device and the fingerprint to be identified.

[0030] Step 102: Obtain first fingerprint data based on the depth information and the image information.

[0031] In step 102, obtaining the first fingerprint data based on the depth information and the image information can be implemented by a fingerprint recognition device. Here, the fingerprint recognition device can combine the collected depth information and image information, pre-process the combined depth information and image information, and generate the first fingerprint data after improving the quality of the input fingerprint data.

[0032] In other embodiments of the present invention, the data format of the first fingerprint data may be in the form of point cloud data; here, point cloud data refers to information of the target object recorded in the form of points, and each point in the point cloud data has a corresponding three-dimensional coordinate; then, the first fingerprint data in this embodiment may be a set of points with three-dimensional coordinates, and the coordinates of the points in the set may truly reflect the spatial structure of the fingerprint; for example, the X-axis of the spatial three-dimensional coordinates of any point in the first data represents the horizontal coordinate information of the specific fingerprint position corresponding to the point, the Y-axis represents the vertical coordinate information of the fingerprint position corresponding to the point, and the Z-axis represents the high and low coordinate information of the fingerprint position corresponding to the point.

[0033] Step 103: Based on the first fingerprint data, perform identification processing on the fingerprint to be identified.

[0034] Among them, step 103 is based on the first fingerprint data, and the identification processing of the fingerprint to be identified can be implemented by a fingerprint identification device; here, the identification processing of the fingerprint to be identified can be based on the first fingerprint data, compared with the fingerprints in the fingerprint database, and the similarity between the first fingerprint and the fingerprints pre-stored in the database is obtained for identification.

[0035] The fingerprint recognition method provided by the embodiment of the present invention collects a fingerprint to be recognized, and obtains depth information and image information of the fingerprint to be recognized, and then obtains first fingerprint data based on the depth information and image information, and finally performs recognition processing on the fingerprint to be recognized based on the first fingerprint data; in this way, when collecting fingerprints, not only the image information of the fingerprint is obtained, but also the depth information of the fingerprint is obtained, and the first fingerprint data is obtained based on the depth information and image information, and then the first fingerprint with the depth information and image information is recognized and processed. In this way, by using information of two dimensions of depth information and image information, the problem of inaccurate recognition of special fingers in the existing fingerprint recognition technology can be solved, and the accuracy of recognition is improved. In addition, the fingerprint collection method for collecting depth information and image information has low requirements on the surrounding environment, thereby reducing the requirements on the environment and the collection cost.

[0036] Based on the above embodiments, the embodiments of the present invention provide a fingerprint recognition method. Figure 2 As shown, the method comprises the following steps:

[0037] Step 201: A fingerprint recognition device collects a fingerprint to be recognized at a first angle through a time-of-flight (TOF) camera to obtain first sub-depth information and first sub-image information of the fingerprint to be recognized; and collects the fingerprint to be recognized at a second angle through the TOF camera to obtain second sub-depth information and second sub-image information of the fingerprint to be recognized.

[0038] The depth information of the fingerprint to be identified consists of first sub-depth information and second sub-depth information, and the image information of the fingerprint to be identified consists of first sub-image information and second sub-image information.

[0039] In other embodiments of the present invention, the TOF camera includes a TOF camera and a red-green-blue (RGB) color camera. Specifically, the TOF camera obtains depth information of the fingerprint to be identified through the TOF camera, and obtains image information of the fingerprint to be identified through the RGB color camera.

[0040] The following explains how the TOF camera obtains the depth information of the fingerprint to be identified.

[0041] The TOF camera can send continuous high-frequency modulated light pulses to the finger in the area to be identified. Here, LED or laser diode is used to emit pulse light, and its pulse frequency can reach 100MHz; then, the change of incident light signal and reflected light signal is used to measure the distance of the fingerprint to be identified. Here, the internal sensor of the TOF camera is used to receive the light pulse returned from the finger in the area to be identified, and the distance between the TOF camera and the finger fingerprint is obtained by detecting the flight (round-trip) information of the light pulse. That is, each imaging unit of the TOF camera records and calculates the phase or time of the incident light going back and forth between the TOF camera and the object, thereby obtaining the depth information of the fingerprint to be identified.

[0042] In other embodiments of the present invention, the fingerprint recognition device obtains image information of the fingerprint to be recognized through an RGB color camera. Here, the RGB color camera uses the principle of total reflection of light to obtain two-dimensional image information of the fingerprint to be recognized.

[0043] In other embodiments of the present invention, in order to obtain complete fingerprint data of a finger, it is necessary to obtain the fingerprint of the entire finger, including the front side (the side opposite to the nail) and two side sides of a finger; in general, the TOF camera collects fingerprints at a fixed angle, so that only part of the fingerprint of the finger can be collected, and the complete fingerprint image cannot be obtained, and fingerprint recognition based on an incomplete fingerprint image is very one-sided; however, in the embodiment of the present invention, a TOF camera is used to obtain fingerprint images at different shooting angles at different shooting angles, thereby ensuring that the complete fingerprint information of the fingerprint to be identified can be obtained. It should be noted that the first angle and the second angle in this embodiment are only used to distinguish the shooting angles, and the words "first" and "second" do not limit the quantity and order.

[0044] In other embodiments of the present invention, the TOF camera collects the fingerprint to be identified at the first shooting angle and the second shooting angle respectively, and the setting of the first shooting angle and the second shooting angle is based on the principle of covering all fingerprint information of the fingerprint to be identified. Among them, the TOF camera will obtain the fingerprint image corresponding to the shooting angle when shooting at each shooting angle, and can obtain the sub-depth information and sub-image information of the fingerprint in each fingerprint image. The sub-depth information at all shooting angles can constitute the depth information of the complete fingerprint to be identified, and the sub-image information at all shooting angles can constitute the image information of the complete fingerprint to be identified.

[0045] Step 202: The fingerprint recognition device generates first sub-fingerprint data based on the first sub-depth information and the first sub-image information; and generates second sub-fingerprint data based on the second sub-depth information and the second sub-image information.

[0046] The sub-depth information and the sub-image information have a corresponding relationship; and the sub-fingerprint data may be in the form of point cloud data.

[0047] In other embodiments of the present invention, the first sub-depth information may correspond to the first sub-image information, and the second sub-depth information may correspond to the second sub-image information. A complete sub-fingerprint data may be obtained by combining the corresponding sub-depth information and sub-image information.

[0048] Step 203: The fingerprint recognition device determines matching feature points of each sub-fingerprint data in the first sub-fingerprint data and the second sub-fingerprint data.

[0049] The first sub-fingerprint data and the second sub-fingerprint data have at least one identical matching feature point.

[0050] In other embodiments of the present invention, each sub-fingerprint data includes at least one matching feature point; here, the matching feature point can be a point where the grayscale value in the point cloud data corresponding to the sub-fingerprint data changes dramatically, or a point or a set of points where the curvature changes greatly in the point cloud data corresponding to the sub-fingerprint data.

[0051] In this embodiment, the first sub-fingerprint data and the second sub-fingerprint data can constitute complete fingerprint data of the finger; therefore, the first sub-fingerprint data and the second sub-fingerprint data have the same matching feature points, and the first sub-fingerprint data and the second sub-fingerprint data can be spliced ​​into complete fingerprint data.

[0052] In other embodiments of the present invention, a Speed ​​Up Robust Features (SURF) algorithm may be used to obtain matching feature points of each sub-fingerprint data.

[0053] Step 204: The fingerprint recognition device obtains a first matrix and a second matrix between matching feature points of the first sub-fingerprint data and matching feature points of the second sub-fingerprint data.

[0054] The first sub-fingerprint data and the second sub-fingerprint data have the same matching feature points, and the first matrix and the second matrix between the first sub-fingerprint data and the second sub-fingerprint data can be calculated according to the same matching feature points in the first sub-fingerprint data and the second sub-fingerprint data.

[0055] In other embodiments of the present invention, obtaining the first matrix between the matching feature points of the first sub-fingerprint data and the second sub-fingerprint data may be achieved in the following manner:

[0056] Calculate the rotation angle between the matching feature points of the first sub-fingerprint data and the matching feature points of the second sub-fingerprint data;

[0057] Here, the rotation angle between the matching feature points of the two sub-fingerprint data may be the rotation angle between the same matching feature points in the first sub-fingerprint data and the second sub-fingerprint data; specifically, the rotation angle may be obtained by calculating the transformation of the linear coordinates between the matching feature points.

[0058] Based on the rotation angle between the matching feature points of the first sub-fingerprint data and the matching feature points of the second sub-fingerprint data, a first matrix between the matching feature points of the first sub-fingerprint data and the matching feature points of the second sub-fingerprint data is obtained.

[0059] The obtained rotation angle data between all identical matching feature points in the first sub-fingerprint data and the second sub-fingerprint data are arranged in a certain order to form a first matrix.

[0060] Similarly, obtaining the second matrix between the matching feature points of the first sub-fingerprint data and the second sub-fingerprint data can be achieved in the following manner:

[0061] Calculate the translation distance between the matching feature points of the first sub-fingerprint data and the matching feature points of the second sub-fingerprint data;

[0062] Here, the translation distance between the matching feature points of the two sub-fingerprint data may be the translation distance between each identical matching feature point in the two sub-fingerprint data.

[0063] Based on the translation distance between the matching feature points of the first sub-fingerprint data and the matching feature points of the second sub-fingerprint data, a second matrix between the matching feature points of the first sub-fingerprint data and the matching feature points of the second sub-fingerprint data is obtained.

[0064] The obtained translation distance data between all identical matching feature points in the first sub-fingerprint data and the second sub-fingerprint data are arranged in a certain order to form a second matrix.

[0065] Step 205: The fingerprint recognition device combines the first sub-fingerprint data and the second sub-fingerprint data based on the first matrix and the second matrix to obtain second fingerprint data.

[0066] The first matrix can reflect the rotation angle of the first sub-fingerprint data and the second sub-fingerprint data, and the second matrix can reflect the translation distance of the first sub-fingerprint data and the second sub-fingerprint data; therefore, the two adjacent sub-fingerprint data can be registered through the first matrix and the second matrix between the matching feature points of the first sub-fingerprint data and the matching feature points of the second sub-fingerprint data; here, one of the first sub-fingerprint data and the second sub-fingerprint data is selected as the reference sub-fingerprint data, and the other sub-fingerprint data is selected as the matching sub-fingerprint data, and the rotation angle of the matching sub-fingerprint data is adjusted according to the first matrix between the matching feature points of the two, and the spatial position of the matching sub-fingerprint data is adjusted according to the second matrix, so that the matching feature points of the matching sub-fingerprint data coincide with the matching feature points of the reference sub-fingerprint data, and the coordinate alignment of the first sub-fingerprint data and the second sub-fingerprint data is completed, and the combination of the first sub-fingerprint data and the second sub-fingerprint data is realized.

[0067] Similarly, through the above method, the coordinates of the first sub-fingerprint data and the second sub-fingerprint data can be aligned and combined into the second fingerprint data.

[0068] Step 206: The fingerprint recognition device pre-processes the second fingerprint data to obtain the first fingerprint data.

[0069] Among them, preprocessing can include noise elimination, positioning and normalization processing. In practical applications, the second fingerprint data is the original fingerprint data obtained by the fingerprint recognition device. Due to the influence of laser scattering, the second fingerprint data inevitably contains data glitches; at the same time, the second fingerprint data is composed of at least two sub-fingerprint data. Therefore, the second fingerprint data is inevitably displaced, rotated, etc. Before fingerprint recognition, the second fingerprint data needs to be unified and converted into a consistent format to obtain high-quality first fingerprint data.

[0070] Step 207: The fingerprint recognition device performs recognition processing on the fingerprint to be recognized based on the first fingerprint data.

[0071] It should be noted that the first and second of the first angle, second angle, first sub-depth information, second sub-depth information, first sub-image information, second sub-image information, first sub-fingerprint data and second sub-fingerprint data in the embodiment of the present invention are merely conceptual limitations and are not used to limit the quantity; in practical applications, the first angle or the second angle may also include multiple angles, and correspondingly, the first sub-depth information or the second sub-depth information may include multiple sub-depth information, the first sub-image information or the second sub-image information may include multiple sub-image information, and the first sub-fingerprint data or the second sub-fingerprint data may include multiple sub-fingerprint data; here, the number of the shooting angle, sub-depth information, sub-image information and sub-fingerprint data is the same, that is, two shooting angles correspond to two sub-depth information, two sub-image information and two sub-fingerprint data.

[0072] It should be noted that the explanations of the same steps or related concepts in this embodiment and other embodiments can refer to the descriptions in other embodiments and will not be repeated here.

[0073] The fingerprint recognition method provided by the embodiment of the present invention collects the fingerprint to be recognized by using a TOF camera, and obtains the depth information and image information of the fingerprint to be recognized, and then obtains the first fingerprint data based on the depth information and the image information, and finally performs recognition processing on the fingerprint to be recognized based on the first fingerprint data; in this way, when performing fingerprint collection, the TOF camera is used for fingerprint collection, not only the image information of the fingerprint can be obtained, but also the depth information of the fingerprint can be obtained, and the first fingerprint data is obtained based on the depth information and the image information, and then the first fingerprint with the depth information and the image information is recognized and processed. In this way, by using the principle of emitting high-frequency light pulses by the TOF camera, the information of two dimensions of depth information and image information can be collected without the user contacting the collection device, which can solve the problem of inaccurate recognition of special fingers in the existing fingerprint recognition technology, improve the accuracy of recognition, and the fingerprint collection method for collecting depth information and image information has low requirements on the surrounding environment; at the same time, the cost of redundant fingerprint chips can be reduced, saving the collection cost.

[0074] Based on the above embodiments, the embodiments of the present invention provide a fingerprint recognition method. Figure 3 As shown, the method comprises the following steps:

[0075] Step 301: The fingerprint recognition device collects the fingerprint to be recognized at a first angle through a TOF camera to obtain first sub-depth information and first sub-image information of the fingerprint to be recognized; collects the fingerprint to be recognized at a second angle through the TOF camera to obtain second sub-depth information and second sub-image information of the fingerprint to be recognized.

[0076] The depth information of the fingerprint to be identified is composed of the first sub-depth information and the second sub-depth information, and the image information of the fingerprint to be identified is composed of the first sub-image information and the second sub-image information.

[0077] Step 302: The fingerprint recognition device generates first sub-fingerprint data based on the first sub-depth information and the first sub-image information; and generates second sub-fingerprint data based on the second sub-depth information and the second sub-image information.

[0078] The sub-depth information and the sub-image information have a corresponding relationship.

[0079] Step 303: The fingerprint recognition device determines matching feature points of each sub-fingerprint data in the first sub-fingerprint data and the second sub-fingerprint data.

[0080] Step 304: The fingerprint recognition device obtains a first matrix and a second matrix between matching feature points of the first sub-fingerprint data and matching feature points of the second sub-fingerprint data.

[0081] The first sub-fingerprint data and the second sub-fingerprint data have at least one identical matching feature point.

[0082] Step 305: The fingerprint recognition device combines the first sub-fingerprint data and the second sub-fingerprint data into second fingerprint data based on the first matrix and the second matrix.

[0083] Step 306: The fingerprint recognition device eliminates noise in the second fingerprint data to obtain third fingerprint data.

[0084] The third data may be in the form of point cloud data.

[0085] In other embodiments of the present invention, eliminating noise in the second fingerprint data may be: smoothing the second fingerprint data, removing violently jittered data or data groups, and removing points with large grayscale jumps according to the grayscale level of each point in the point cloud data corresponding to the second fingerprint data.

[0086] Step 307: The fingerprint recognition device selects a fingerprint center point in the third fingerprint data, and corrects the direction of the third fingerprint data based on the fingerprint center point to obtain fourth fingerprint data.

[0087] The fourth data may be in the form of point cloud data.

[0088] In other embodiments of the present invention, the fingerprint center point may be a point or a set of points with the largest curvature in the point cloud data corresponding to the third fingerprint data; the direction of the third fingerprint may refer to the distribution of the third fingerprint relative to the fingerprint center point. The fingerprint center point is used as a reference point, and the change trend of the data around the fingerprint center point in the third fingerprint data and the distribution trend of the data are compared to determine the direction of the third fingerprint, and the coordinates of the third fingerprint data after the direction is determined are adjusted to obtain the fourth fingerprint data.

[0089] Step 308: The fingerprint recognition device adjusts the first parameter value of the image information in the fourth fingerprint data to the first preset parameter value and the second parameter value of the depth information in the fourth fingerprint data to the second preset parameter value to obtain the first fingerprint data.

[0090] The first parameter value may be a ratio of the length to the width of the fingerprint image corresponding to the image information in the fourth fingerprint data. Specifically, the fingerprint recognition device may proportionally adjust the data corresponding to the image information in the fourth fingerprint data to the first preset value.

[0091] In other embodiments of the present invention, the second parameter value may be a ratio of data corresponding to the depth information in the fourth fingerprint data. Specifically, the fingerprint recognition device may proportionally adjust the data corresponding to the depth information in the fourth fingerprint data to the second preset value.

[0092] Step 309: The fingerprint recognition device extracts fingerprint features from the first fingerprint data.

[0093] The fingerprint features include the overall features and local features of the fingerprint. Here, the overall features of the fingerprint include: the shape of the fingerprint pattern, such as dustpan, bucket, bow, etc.; the local features of the fingerprint include: the fingerprint center point with depth information, triangle point, breakpoint, intersection point and bifurcation point, etc.

[0094] In other embodiments of the present invention, the fingerprint recognition device may extract fingerprint features from the first fingerprint data by principal component analysis, kernel principal component analysis, point graph relaxation matching, minimum distance graph method, triangulation transformation method, and the like.

[0095] Step 310: The fingerprint recognition device uses a preset method to match the fingerprint features with the pre-stored fingerprint features in the fingerprint library.

[0096] Among them, before step 310, the fingerprint recognition device can use a classifier to classify the fingerprint features pre-stored in the fingerprint library, providing a retrieval mechanism for a large fingerprint database; and stable and accurate classification can greatly reduce the time for fingerprint retrieval and matching. The fingerprint recognition device can classify fingerprints into several categories based on the overall characteristics of the fingerprint; for example, the fingerprint recognition device can first classify the fingerprints according to the overall characteristics, that is, the fingerprint lines, into four categories: dustpan type, bucket type, bow type and mixed type; and then subdivide the above fingerprint types according to the characteristics of each category, such as the dustpan type is further divided into left dustpan type and right dustpan type. Common classifiers can include nearest neighbor distance classifiers, artificial neural network classifiers, support vector machine (SVM) classifiers, etc.

[0097] In other embodiments of the present invention, the fingerprint recognition device uses a preset method to match the fingerprint feature with the pre-stored fingerprint feature in the fingerprint library. Specifically, the fingerprint recognition device first selects the corresponding fingerprint category library in the fingerprint library based on the overall feature of the fingerprint; then compares the similarity between the local fingerprint feature and a certain fingerprint feature set pre-stored in the corresponding fingerprint category library, and compares it with a preset threshold to determine whether the fingerprint feature and the pre-stored fingerprint feature are from the same fingerprint.

[0098] Optionally, other embodiments of the present invention may further perform the following steps.

[0099] Step 311: If the fingerprint feature matches the pre-stored fingerprint feature successfully, the fingerprint recognition device updates the pre-stored fingerprint feature in the fingerprint database based on the fingerprint feature.

[0100] Among them, if the fingerprint feature successfully matches the pre-stored fingerprint feature, the fingerprint recognition device obtains the currently extracted fingerprint feature and compares the currently extracted fingerprint feature with the pre-stored fingerprint feature that successfully matches in the fingerprint library; if the currently extracted fingerprint feature has a feature that is not included in the pre-stored fingerprint in the fingerprint library that successfully matches the current fingerprint feature, the feature is saved in the pre-stored fingerprint feature.

[0101] Compared with the existing fingerprint recognition technology that can only obtain two-dimensional fingerprint image information, the fingerprint recognition method provided by the embodiment of the present invention can collect the fingerprint to be recognized through the TOF camera, and simultaneously obtain the depth information and image information of the fingerprint to be recognized, which not only has the two-dimensional fingerprint image information, but also includes the information of the uneven surface fluctuation of the fingerprint to be recognized; in this way, the fingerprint recognition is performed using the extracted fingerprint features with depth information, which overcomes the defect of inaccurate recognition of special fingers (dry fingers, wet fingers, etc.) in the prior art, and improves the accuracy of fingerprint recognition. In addition, the TOF camera uses the principle of total reflection of light and emitting high-frequency modulated light pulses to the fingerprint to be recognized, and can obtain fingerprint information without contacting the fingerprint collection device, reducing the requirements for the environment; further, the use of the TOF camera can avoid the use of redundant fingerprint chips, reducing the cost of fingerprint recognition.

[0102] It should be noted that the explanations of the same steps or related concepts in this embodiment and other embodiments can refer to the descriptions in other embodiments and will not be repeated here.

[0103] The fingerprint recognition method provided by the embodiment of the present invention collects the fingerprint to be recognized by using a TOF camera, and obtains the depth information and image information of the fingerprint to be recognized, and then obtains the first fingerprint data based on the depth information and the image information, and finally performs recognition processing on the fingerprint to be recognized based on the first fingerprint data; in this way, when performing fingerprint collection, the TOF camera is used for fingerprint collection, not only the image information of the fingerprint can be obtained, but also the depth information of the fingerprint can be obtained, and the first fingerprint data is obtained based on the depth information and the image information, and then the first fingerprint with the depth information and the image information is recognized and processed. In this way, by using the principle of emitting high-frequency light pulses by the TOF camera, the information of two dimensions of depth information and image information can be collected without the user contacting the collection device, which can solve the problem of inaccurate recognition of special fingers in the existing fingerprint recognition technology, improve the accuracy of recognition, and the fingerprint collection method for collecting depth information and image information has low requirements on the surrounding environment; at the same time, the cost of redundant fingerprint chips can be reduced, saving the collection cost.

[0104] Based on the above embodiments, refer to Figure 4As shown, first, the TOF camera collects the fingerprint to be identified and generates fingerprint data. Here, the specific process of the TOF camera performing fingerprint collection and the fingerprint data generation process are the same as those of other embodiments of the present invention, which will not be described in detail here; the generated fingerprint data is preprocessed, including denoising, positioning and normalizing the fingerprint data. Here, the specific denoising, positioning and normalization processes are the same as those of other embodiments of the present invention, which will not be described in detail here; then, the fingerprint data after preprocessing is subjected to fingerprint feature extraction; based on the selected or designed classifier, the extracted fingerprint features are matched with the pre-stored fingerprint features in the fingerprint library. Here, the specific matching process is the same as that of other embodiments of the present invention, which will not be described in detail here; finally, the matching result is obtained and output.

[0105] Based on the above embodiments, an embodiment of the present invention provides a fingerprint recognition device, which can be applied to Figures 1 to 3 In the fingerprint recognition method provided in the corresponding embodiment, refer to Figure 5 As shown, the fingerprint recognition device 5 may include: a processor 51, a storage medium 52 configured to store executable instructions, and a communication bus 53, wherein:

[0106] The communication bus 53 is used to realize the communication connection between the processor 51 and the memory 52;

[0107] The processor 51 is used to execute the program for fingerprint identification stored in the memory to implement the following steps:

[0108] Collect the fingerprint to be identified, and obtain the depth information and image information of the fingerprint to be identified;

[0109] Obtaining first fingerprint data based on the depth information and the image information;

[0110] Based on the first fingerprint data, the fingerprint to be identified is identified.

[0111] In other embodiments of the present invention, when the processor 51 is used to execute the steps of collecting the fingerprint to be identified and obtaining the depth information and image information of the fingerprint to be identified stored in the memory, the following steps may also be implemented:

[0112] The fingerprint to be identified is collected by the TOF camera to obtain the depth information and image information of the fingerprint to be identified.

[0113] In other embodiments of the present invention, the processor 51 is used to execute the steps stored in the memory to collect the fingerprint to be identified by the TOF camera and obtain the depth information and image information of the fingerprint to be identified, and can also implement the following steps:

[0114] The fingerprint to be identified is collected at a first angle by a TOF camera to obtain first sub-depth information and first sub-image information of the fingerprint to be identified; the fingerprint to be identified is collected at a second angle by a TOF camera to obtain second sub-depth information and second sub-image information of the fingerprint to be identified; wherein the depth information of the fingerprint to be identified is composed of the first sub-depth information and the second sub-depth information, and the image information of the fingerprint to be identified is composed of the first sub-image information and the second sub-image information.

[0115] In other embodiments of the present invention, the processor 51 is used to execute the depth information and the image information stored in the memory to obtain the first fingerprint data, and can also implement the following steps:

[0116] Generate first sub-fingerprint data based on the first sub-depth information and the first sub-image information; generate second sub-fingerprint data based on the second sub-depth information and the second sub-image information;

[0117] generating second fingerprint data based on the first sub-fingerprint data and the second sub-fingerprint data;

[0118] The second fingerprint data is preprocessed to obtain the first fingerprint data.

[0119] In other embodiments of the present invention, the processor 51 is used to execute the first sub-fingerprint data and the second sub-fingerprint data stored in the memory to generate the second fingerprint data, and can also implement the following steps:

[0120] Determine a matching feature point of each sub-fingerprint data in the first sub-fingerprint data and the second sub-fingerprint data; wherein the first sub-fingerprint data and the second sub-fingerprint data have at least one common matching feature point;

[0121] Acquire a first matrix and a second matrix between matching feature points of the first sub-fingerprint data and matching feature points of the second sub-fingerprint data;

[0122] Based on the first matrix and the second matrix, the first sub-fingerprint data and the second sub-fingerprint data are combined to obtain the second fingerprint data.

[0123] In other embodiments of the present invention, when the processor 51 is used to execute the first matrix and the second matrix between the matching feature points of the first sub-fingerprint data and the matching feature points of the second sub-fingerprint data stored in the memory, the following steps may also be implemented:

[0124] Calculate the rotation angle and translation distance between the matching feature points of the first sub-fingerprint data and the matching feature points of the second sub-fingerprint data;

[0125] Acquire a first matrix between the matching feature points of the first sub-fingerprint data and the matching feature points of the second sub-fingerprint data based on a rotation angle between the matching feature points of the first sub-fingerprint data and the matching feature points of the second sub-fingerprint data;

[0126] Based on the translation distance between the matching feature points of the first sub-fingerprint data and the matching feature points of the second sub-fingerprint data, a second matrix between the matching feature points of the first sub-fingerprint data and the matching feature points of the second sub-fingerprint data is obtained.

[0127] In other embodiments of the present invention, the TOF camera includes a TOF camera and an RGB color camera. When the processor 51 is used to execute the depth information and image information of the fingerprint to be identified using the time-of-flight TOF camera stored in the memory, the following steps may also be implemented:

[0128] Obtain the depth information of the fingerprint to be identified through the TOF camera;

[0129] The image information of the fingerprint to be identified is obtained through an RGB color camera.

[0130] In other embodiments of the present invention, the processor 51 is used to perform the denoising, positioning and normalization processing on the second fingerprint data stored in the memory to obtain the first fingerprint data, and can also implement the following steps:

[0131] Eliminating noise in the second fingerprint data to obtain third fingerprint data;

[0132] Selecting a fingerprint center point in the third fingerprint data, and correcting the direction of the third fingerprint data based on the fingerprint center point to obtain fourth fingerprint data;

[0133] The first parameter value of the image information in the fourth fingerprint data is adjusted to a first preset value and the second parameter value of the depth information in the fourth fingerprint data is adjusted to a second preset value to obtain the first fingerprint data.

[0134] In other embodiments of the present invention, the processor 51 is used to execute the identification processing based on the first fingerprint data stored in the memory, and can also implement the following steps:

[0135] Extracting fingerprint features from the first fingerprint data; wherein the fingerprint features include overall features and local features of the fingerprint;

[0136] The fingerprint features are matched with the pre-stored fingerprint features in the fingerprint library using a preset method.

[0137] In other embodiments of the present invention, after the processor 51 is used to execute the fingerprint features stored in the memory and match and identify the fingerprint features pre-stored in the fingerprint library using a preset method, the following steps may also be implemented:

[0138] If the fingerprint feature matches the pre-stored fingerprint feature successfully, the pre-stored fingerprint feature in the fingerprint database is updated based on the fingerprint feature.

[0139] It should be noted that the specific implementation process of the steps executed by the processor in this embodiment can refer to Figures 1 to 3 The implementation process of the fingerprint recognition method provided in the corresponding embodiment will not be repeated here.

[0140] The fingerprint recognition device provided by the embodiment of the present invention collects the fingerprint to be recognized and obtains the depth information and image information of the fingerprint to be recognized, and then obtains the first fingerprint data based on the depth information and the image information, and finally performs recognition processing on the fingerprint to be recognized based on the first fingerprint data; in this way, when collecting fingerprints, not only the image information of the fingerprint is obtained, but also the depth information of the fingerprint is obtained, and the first fingerprint data is obtained based on the depth information and the image information, and then the first fingerprint with the depth information and the image information is recognized and processed. In this way, by using the information of the two dimensions of depth information and image information, the problem of inaccurate recognition of special fingers in the existing fingerprint recognition technology can be solved, and the accuracy of recognition is improved. In addition, the fingerprint collection method of collecting depth information and image information has low requirements on the surrounding environment, which reduces the requirements on the environment and the collection cost.

[0141] Based on the foregoing embodiments, an embodiment of the present invention provides a computer-readable storage medium, which stores one or more programs, and the one or more programs can be executed by one or more processors to implement the following steps:

[0142] Collect the fingerprint to be identified, and obtain the depth information and image information of the fingerprint to be identified;

[0143] Obtaining first fingerprint data based on the depth information and the image information;

[0144] Based on the first fingerprint data, the fingerprint to be identified is identified.

[0145] In other embodiments of the present invention, when the one or more programs can be executed by one or more processors to collect the fingerprint to be identified and obtain the depth information and image information of the fingerprint to be identified, the following steps can also be implemented:

[0146] The fingerprint to be identified is collected by the TOF camera to obtain the depth information and image information of the fingerprint to be identified.

[0147] In other embodiments of the present invention, the one or more programs may be executed by one or more processors to collect the fingerprint to be identified through the TOF camera, and when the depth information and image information of the fingerprint to be identified are obtained, the following steps may also be implemented:

[0148] The fingerprint to be identified is collected at a first angle by a TOF camera to obtain first sub-depth information and first sub-image information of the fingerprint to be identified; the fingerprint to be identified is collected at a second angle by a TOF camera to obtain second sub-depth information and second sub-image information of the fingerprint to be identified; wherein the depth information of the fingerprint to be identified is composed of the first sub-depth information and the second sub-depth information, and the image information of the fingerprint to be identified is composed of the first sub-image information and the second sub-image information.

[0149] In other embodiments of the present invention, the one or more programs may be executed by one or more processors to obtain the first fingerprint data based on the depth information and the image information, and the following steps may also be implemented:

[0150] Generate first sub-fingerprint data based on the first sub-depth information and the first sub-image information; generate second sub-fingerprint data based on the second sub-depth information and the second sub-image information;

[0151] generating second fingerprint data based on the first sub-fingerprint data and the second sub-fingerprint data;

[0152] The second fingerprint data is preprocessed to obtain the first fingerprint data.

[0153] In other embodiments of the present invention, the one or more programs may be executed by one or more processors to generate the second fingerprint data based on the first sub-fingerprint data and the second sub-fingerprint data, and the following steps may also be implemented:

[0154] Determine a matching feature point of each sub-fingerprint data in the first sub-fingerprint data and the second sub-fingerprint data; wherein the first sub-fingerprint data and the second sub-fingerprint data have at least one common matching feature point;

[0155] Acquire a first matrix and a second matrix between matching feature points of the first sub-fingerprint data and matching feature segments of the second sub-fingerprint data;

[0156] Based on the first matrix and the second matrix, the first sub-fingerprint data and the second sub-fingerprint data are combined to obtain the second fingerprint data.

[0157] In other embodiments of the present invention, when the one or more programs can be executed by one or more processors to obtain the first matrix and the second matrix between the matching feature points of the first sub-fingerprint data and the matching feature segments of the second sub-fingerprint data, the following steps may also be implemented:

[0158] Calculate the rotation angle and translation distance between the matching feature points of the first sub-fingerprint data and the matching feature segments of the second sub-fingerprint data;

[0159] Based on the rotation angle between the matching feature points of the first sub-fingerprint data and the matching feature segments of the second sub-fingerprint data, obtaining a first matrix between the matching feature points of the first sub-fingerprint data and the matching feature segments of the second sub-fingerprint data;

[0160] Based on the translation distance between the matching feature points of the first sub-fingerprint data and the matching feature segments of the second sub-fingerprint data, a second matrix between the matching feature points of the first sub-fingerprint data and the matching feature segments of the second sub-fingerprint data is obtained.

[0161] In other embodiments of the present invention, the TOF camera includes a TOF camera and an RGB color camera, and the one or more programs can be executed by one or more processors. When the TOF camera is used to obtain the depth information and image information of the fingerprint to be identified, the following steps can also be implemented:

[0162] Obtain the depth information of the fingerprint to be identified through the TOF camera;

[0163] The image information of the fingerprint to be identified is obtained through an RGB color camera.

[0164] In other embodiments of the present invention, the one or more programs may be executed by one or more processors to perform noise elimination, positioning and normalization processing on the second fingerprint data, and when the first fingerprint data is obtained, the following steps may also be implemented:

[0165] Eliminating noise in the second fingerprint data to obtain third fingerprint data;

[0166] Selecting a fingerprint center point in the third fingerprint data, and correcting the direction of the third fingerprint data based on the fingerprint center point to obtain fourth fingerprint data;

[0167] The first parameter value of the image information in the fourth fingerprint data is adjusted to a first preset value and the second parameter value of the depth information in the fourth fingerprint data is adjusted to a second preset value to obtain the first fingerprint data.

[0168] In other embodiments of the present invention, the one or more programs may be executed by one or more processors, and when performing identification processing on the fingerprint to be identified based on the first fingerprint data, the following steps may also be implemented:

[0169] Extracting fingerprint features from the first fingerprint data; wherein the fingerprint features include overall features and local features of the fingerprint;

[0170] The fingerprint features are matched with the pre-stored fingerprint features in the fingerprint library using a preset method.

[0171] In other embodiments of the present invention, the one or more programs may be executed by one or more processors to match and identify the fingerprint features with the fingerprint features pre-stored in the fingerprint library using a preset method, and then the following steps may be implemented:

[0172] If the fingerprint feature matches the pre-stored fingerprint feature successfully, the pre-stored fingerprint feature in the fingerprint database is updated based on the fingerprint feature.

[0173] It should be noted that the specific implementation process of the steps performed in this embodiment can refer to Figures 1 to 3 The implementation process of the fingerprint recognition method provided in the corresponding embodiment will not be repeated here.

[0174] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of hardware embodiments, software embodiments, or embodiments combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage and optical storage, etc.) containing computer-usable program code.

[0175] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0176] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0177] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0178] The above description is only a preferred embodiment of the present invention and is not intended to limit the protection scope of the present invention.

Claims

1. A fingerprint recognition method, characterized in that: The method comprises: Collecting a fingerprint to be identified, and obtaining depth information and image information of the fingerprint to be identified, wherein the depth information includes distance information between a device for collecting fingerprints and the fingerprint to be identified; Based on the depth information and the image information, obtaining first fingerprint data; Based on the first fingerprint data, performing identification processing on the fingerprint to be identified; The collecting of the fingerprint to be identified and obtaining the depth information and image information of the fingerprint to be identified includes: Capturing the fingerprint to be identified at a first angle to obtain first sub-depth information and first sub-image information of the fingerprint to be identified; Capturing the fingerprint to be identified at a second angle to obtain second sub-depth information and second sub-image information of the fingerprint to be identified; Determine the depth information of the fingerprint to be identified according to the first sub-depth information and the second sub-depth information, and determine the image information of the fingerprint to be identified according to the first sub-image information and the second sub-image information; The obtaining first fingerprint data based on the depth information and the image information includes: generating first sub-fingerprint data based on the first sub-depth information and the first sub-image information; generating second sub-fingerprint data based on the second sub-depth information and the second sub-image information; Calculate the rotation angle and translation distance between the matching feature points of the first sub-fingerprint data and the matching feature points of the second sub-fingerprint data; Combining the first sub-fingerprint data with the second sub-fingerprint data to obtain second fingerprint data according to a rotation angle and a translation distance between matching feature points of the first sub-fingerprint data and matching feature points of the second sub-fingerprint data; The second fingerprint data is preprocessed to obtain the first fingerprint data.

2. The method according to claim 1, characterized in that The collecting of the fingerprint to be identified and obtaining the depth information and image information of the fingerprint to be identified includes: The fingerprint to be identified is collected by a time-of-flight TOF camera to obtain depth information and image information of the fingerprint to be identified.

3. The method according to claim 2, characterized in that The combining the first sub-fingerprint data and the second sub-fingerprint data to obtain the second fingerprint data includes: Determine a matching feature point of each sub-fingerprint data in the first sub-fingerprint data and the second sub-fingerprint data; wherein the first sub-fingerprint data and the second sub-fingerprint data have at least one common matching feature point; Acquire a first matrix and a second matrix between matching feature points of the first sub-fingerprint data and matching feature points of the second sub-fingerprint data; Based on the first matrix and the second matrix, the first sub-fingerprint data and the second sub-fingerprint data are combined to obtain the second fingerprint data.

4. The method according to claim 3, characterized in that The step of obtaining a first matrix and a second matrix between matching feature points of the first sub-fingerprint data and matching feature points of the second sub-fingerprint data includes: Based on the rotation angle between the matching feature points of the first sub-fingerprint data and the matching feature points of the second sub-fingerprint data, obtaining a first matrix between the matching feature points of the first sub-fingerprint data and the matching feature points of the second sub-fingerprint data; Based on the translation distance between the matching feature points of the first sub-fingerprint data and the matching feature points of the second sub-fingerprint data, a second matrix between the matching feature points of the first sub-fingerprint data and the matching feature points of the second sub-fingerprint data is obtained.

5. The method according to any one of claims 2 to 4, characterized in that: The time-of-flight TOF camera includes a TOF camera and a red-green-blue RGB color camera. The method of collecting the fingerprint to be identified by the time-of-flight TOF camera to obtain the depth information and image information of the fingerprint to be identified includes: Acquire the depth information of the fingerprint to be identified through the TOF camera; The image information of the fingerprint to be identified is obtained through the RGB color camera.

6. The method according to claim 1, characterized in that The preprocessing of the second fingerprint data to obtain the first fingerprint data includes: Eliminating noise in the second fingerprint data to obtain third fingerprint data; Selecting a fingerprint center point in the third fingerprint data, and correcting the direction of the third fingerprint data based on the fingerprint center point to obtain fourth fingerprint data; The first fingerprint data is obtained by adjusting the first parameter value of the image information in the fourth fingerprint data to a first preset value and the second parameter value of the depth information in the fourth fingerprint data to a second preset value.

7. The method according to claim 1, characterized in that The step of performing identification processing on the fingerprint to be identified based on the first fingerprint data includes: Extracting fingerprint features from the first fingerprint data; wherein the fingerprint features include overall features and local features of the fingerprint; The fingerprint feature is matched with the pre-stored fingerprint features in the fingerprint library using a preset method.

8. The method according to claim 7, characterized in that After the fingerprint feature is matched and identified with the fingerprint feature pre-stored in the fingerprint library by the preset method, the method further includes: If the fingerprint feature matches the pre-stored fingerprint feature successfully, the pre-stored fingerprint feature in the fingerprint database is updated based on the fingerprint feature.

9. The method according to claim 7, characterized in that: The overall features of the fingerprint include: the shape of the fingerprint lines; the local features of the fingerprint include: the fingerprint center point, triangle point, breakpoint, intersection point and bifurcation point with depth information.

10. A fingerprint recognition device, characterized in that: The fingerprint recognition device at least includes: a processor and a storage medium configured to store executable instructions, wherein: The processor is configured to execute stored executable instructions, the executable instructions comprising: Collecting a fingerprint to be identified, and obtaining depth information and image information of the fingerprint to be identified, wherein the depth information includes distance information between a device for collecting fingerprints and the fingerprint to be identified; Based on the depth information and the image information, obtaining first fingerprint data; Based on the first fingerprint data, performing identification processing on the fingerprint to be identified; The collecting of the fingerprint to be identified and obtaining the depth information and image information of the fingerprint to be identified includes: Capturing the fingerprint to be identified at a first angle to obtain first sub-depth information and first sub-image information of the fingerprint to be identified; Capturing the fingerprint to be identified at a second angle to obtain second sub-depth information and second sub-image information of the fingerprint to be identified; Determine the depth information of the fingerprint to be identified according to the first sub-depth information and the second sub-depth information, and determine the image information of the fingerprint to be identified according to the first sub-image information and the second sub-image information; The obtaining first fingerprint data based on the depth information and the image information includes: generating first sub-fingerprint data based on the first sub-depth information and the first sub-image information; generating second sub-fingerprint data based on the second sub-depth information and the second sub-image information; Calculate the rotation angle and translation distance between the matching feature points of the first sub-fingerprint data and the matching feature points of the second sub-fingerprint data; Combining the first sub-fingerprint data with the second sub-fingerprint data to obtain second fingerprint data according to a rotation angle and a translation distance between matching feature points of the first sub-fingerprint data and matching feature points of the second sub-fingerprint data; The second fingerprint data is preprocessed to obtain the first fingerprint data.

11. The device according to claim 10, characterized in that The processor also implements the following steps: The fingerprint to be identified is collected by a time-of-flight TOF camera to obtain depth information and image information of the fingerprint to be identified.

12. The device according to claim 11, characterized in that The processor also implements the following steps: Determine a matching feature point of each sub-fingerprint data in the first sub-fingerprint data and the second sub-fingerprint data; wherein the first sub-fingerprint data and the second sub-fingerprint data have at least one common matching feature point; Acquire a first matrix and a second matrix between matching feature points of the first sub-fingerprint data and matching feature points of the second sub-fingerprint data; Based on the first matrix and the second matrix, the first sub-fingerprint data and the second sub-fingerprint data are combined to obtain the second fingerprint data.

13. The device according to claim 12, characterized in that The processor also implements the following steps: Based on the rotation angle between the matching feature points of the first sub-fingerprint data and the matching feature points of the second sub-fingerprint data, obtaining a first matrix between the matching feature points of the first sub-fingerprint data and the matching feature points of the second sub-fingerprint data; Based on the translation distance between the matching feature points of the first sub-fingerprint data and the matching feature points of the second sub-fingerprint data, a second matrix between the matching feature points of the first sub-fingerprint data and the matching feature points of the second sub-fingerprint data is obtained.

14. The device according to any one of claims 11 to 13, characterized in that: The time-of-flight TOF camera includes a TOF camera and an RGB color camera, and the processor further implements the following steps: Acquire the depth information of the fingerprint to be identified through the TOF camera; The image information of the fingerprint to be identified is obtained through the RGB color camera.

15. The device according to claim 10, characterized in that The processor also implements the following steps: Eliminating noise in the second fingerprint data to obtain third fingerprint data; Selecting a fingerprint center point in the third fingerprint data, and correcting the direction of the third fingerprint data based on the fingerprint center point to obtain fourth fingerprint data; The first fingerprint data is obtained by adjusting the first parameter value of the image information in the fourth fingerprint data to a first preset value and the second parameter value of the depth information in the fourth fingerprint data to a second preset value.

16. The device according to claim 10, characterized in that The processor also implements the following steps: Extracting fingerprint features from the first fingerprint data; wherein the fingerprint features include overall features and local features of the fingerprint; The fingerprint feature is matched with the pre-stored fingerprint features in the fingerprint library using a preset method.

17. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are configured to execute the fingerprint recognition method according to any one of claims 1 to 9.

Images