An identity authentication method, device, apparatus, and storage medium

Abstract

Embodiments of the present application disclose an identity authentication method, device and equipment, and a storage medium. The method determines a first key point of a first signature handwriting through a multi-resolution analysis manner; performs key point matching on the first key point and a second key point to obtain a key point matching pair; determines a matched first handwriting segment and a second handwriting segment according to the key point matching pair; and authenticates the first signature handwriting according to a distance between the matched first handwriting segment and the second handwriting segment. That is, the embodiments of the present application use signature handwriting to perform identity authentication, which can effectively avoid adverse consequences caused by username and password leakage, and at the same time, the key points of the first signature handwriting are determined by using a multi-resolution analysis manner, the influence of different resolutions on the key points is considered, and the accuracy of the key points is improved. Therefore, the accuracy of an authentication result can be improved when the first signature handwriting is authenticated based on the key points in the subsequent process, and thus the security of identity authentication can be improved.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to an identity authentication method, apparatus, device, and storage medium. Background Technology

[0002] User login is a common scenario in many products. It is a way to authenticate a user's identity. For example, a user can only log in successfully after successful authentication; otherwise, the login will fail.

[0003] Currently, authentication is mainly done through usernames and passwords. For example, in a classroom environment, if a teacher needs to log in to a teaching device or system, they need to enter their username and password under the students' watchful eyes, which makes usernames and passwords easy to leak and results in low security.

[0004] Application content

[0005] This application provides an identity authentication method, apparatus, device, and storage medium, which can improve the security of identity authentication.

[0006] In a first aspect, embodiments of this application provide an identity authentication method, including:

[0007] Obtain the first signature handwriting;

[0008] The first key point of the first signature handwriting was determined by multi-resolution analysis.

[0009] The first and second key points are matched to obtain key point matching pairs. The second key point is the key point of the reference signature handwriting.

[0010] Based on the key point matching pair, determine the first and second handwriting segments that match. The first handwriting segment is the handwriting segment formed by the first key point in the first signature handwriting, and the second handwriting segment is the handwriting segment formed by the second key point in the reference signature handwriting.

[0011] The first signature handwriting is authenticated based on the distance between the first and second matching handwriting segments.

[0012] Secondly, embodiments of this application provide an identity authentication device, including an acquisition module, a determination module, a matching module, and an authentication module;

[0013] The acquisition module is used to acquire the first signature handwriting.

[0014] The determination module is used to determine the first key point of the first signature handwriting through multi-resolution analysis;

[0015] The matching module is used to perform key point matching on the first key point and the second key point to obtain key point matching pairs. The second key point is the key point of the reference signature handwriting.

[0016] The determination module is also used to determine the first and second handwriting segments based on the key point matching pairs. The first handwriting segment is the handwriting segment formed by the first key point in the first signature handwriting, and the second handwriting segment is the handwriting segment formed by the second key point in the reference signature handwriting.

[0017] The authentication module is used to authenticate the first signature handwriting based on the distance between the first and second matching handwriting segments.

[0018] Thirdly, embodiments of this application provide an electronic device, including:

[0019] processor;

[0020] Memory is used to store computer program instructions;

[0021] A touchscreen is used to receive the first signature handwriting.

[0022] When computer program instructions are executed by the processor, the method described in the first aspect is implemented.

[0023] Fourthly, embodiments of this application provide a computer-readable storage medium having computer program instructions stored thereon, which, when executed by a processor, implement the method described in the first aspect.

[0024] Fifthly, embodiments of this application provide a computer program product in which instructions, when executed by a processor of an electronic device, cause the electronic device to perform the method described in the first aspect.

[0025] The identity authentication method, apparatus, device, and storage medium provided in this application embodiment acquire a first signature handwriting, determine a first key point of the first signature handwriting through multi-resolution analysis, perform key point matching on the first key point and a second key point to obtain a key point matching pair, and use the second key point as a key point of the reference signature handwriting; determine a matching first handwriting segment and a matching second handwriting segment based on the key point matching pair; and authenticate the first signature handwriting based on the distance between the matching first handwriting segment and the second handwriting segment. Compared with traditional schemes that use usernames and passwords to authenticate user identities, this application embodiment uses signature handwriting for identity authentication, which can effectively avoid adverse consequences caused by the leakage of usernames and passwords. At the same time, by using multi-resolution analysis to determine the key points of the first signature handwriting, the influence of different resolutions on the key points is considered, improving the accuracy of the key points. Thus, when authenticating the first signature handwriting based on key points in subsequent processes, the accuracy of the authentication results can be improved, thereby enhancing the security of identity authentication. Attached Figure Description

[0026] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the embodiments of this application will be briefly introduced below. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0027] Figure 1 A flowchart illustrating an identity authentication method provided in this application embodiment;

[0028] Figure 2 A flowchart illustrating another authentication method provided in this application embodiment;

[0029] Figure 3 This application provides a schematic diagram of the distribution of a third key point in an embodiment.

[0030] Figure 4 A flowchart illustrating another authentication method provided in this application embodiment;

[0031] Figure 5 A structural diagram of an identity authentication device provided in an embodiment of this application;

[0032] Figure 6 This is a structural diagram of an electronic device provided in an embodiment of this application. Detailed Implementation

[0033] The features and exemplary embodiments of various aspects of this application will now be described in detail. To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only configured to explain this application and are not configured to limit this application. For those skilled in the art, this application can be implemented without some of these specific details. The following description of the embodiments is merely to provide a better understanding of this application by illustrating examples of this application.

[0034] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus that includes said element.

[0035] As mentioned above, in user login scenarios, authentication is currently mainly done through usernames and passwords. For example, in a classroom environment, if a teacher needs to log in to a teaching device or system, they need to enter their username and password under the students' watchful eyes, which makes usernames and passwords easy to leak and results in low security.

[0036] Therefore, embodiments of this application provide an identity authentication method, apparatus, device, and storage medium, which can improve the security of identity authentication. The identity authentication method, apparatus, device, and storage medium provided in this application can be applied not only to classroom environments but also to other environments requiring user identity authentication.

[0037] The identity authentication method provided in this application will be described below with reference to specific embodiments. The identity authentication method provided in this application can be applied to smart devices with data processing functions, such as interactive tablets and other interactive devices. The interactive device may include a touch screen, through which users can realize multi-touch input, such as inputting signature handwriting through the touch screen.

[0038] Figure 1 This is a flowchart illustrating an identity authentication method provided in an embodiment of this application. Figure 1 As shown, the authentication method may include the following steps:

[0039] S110, Obtain the first signature handwriting.

[0040] S120. Determine the first key point of the first signature handwriting through multi-resolution analysis.

[0041] S130. Perform keypoint matching on the first keypoint and the second keypoint to obtain keypoint matching pairs.

[0042] The second key point is the key point of the signature handwriting.

[0043] S140. Based on the key point matching pairs, determine the first and second stroke segments to be matched.

[0044] The first handwriting segment is the handwriting segment formed by the first key point in the first signature handwriting, and the second handwriting segment is the handwriting segment formed by the second key point in the reference signature handwriting.

[0045] S150. Authenticate the first signature handwriting based on the distance between the first and second matching handwriting segments.

[0046] This application embodiment obtains a first signature handwriting and determines a first key point of the first signature handwriting through multi-resolution analysis; it then performs key point matching on the first and second key points to obtain a key point matching pair, with the second key point serving as a key point for the reference signature handwriting; based on the key point matching pair, it determines a matching first handwriting segment and a matching second handwriting segment; and it authenticates the first signature handwriting based on the distance between the matching first and second handwriting segments. Compared to traditional schemes that use usernames and passwords to authenticate user identities, this application embodiment uses signature handwriting for identity authentication, which can effectively avoid adverse consequences caused by the leakage of usernames and passwords. Furthermore, by using multi-resolution analysis to determine the key points of the first signature handwriting, it considers the impact of different resolutions on the key points, improving the accuracy of the key points. Thus, in subsequent authentication of the first signature handwriting based on key points, the accuracy of the authentication result can be improved, thereby enhancing the security of identity authentication.

[0047] The above steps are explained in detail below:

[0048] In S110, the first signature can be a handwritten signature entered by the user via the touchscreen, and the user's identity can be verified through the first signature. This embodiment of the application utilizes the user's handwritten signature for identity verification, which can effectively avoid the impact of username or password leakage, and can fully utilize the touch characteristics of the touchscreen.

[0049] Specifically, the position of the touch point can be sampled according to the set sampling rate to obtain the first signature handwriting.

[0050] In S120, the first key point is a point on the first signature handwriting that satisfies a certain characteristic. For example, the first key point can be a point on the first signature handwriting with a curvature greater than a preset curvature, or it can be a point where the angle formed by the line connecting it and the two points before and after it is less than a preset angle.

[0051] Considering that the screen resolution of the touch screen may vary in different scenarios, or that different users may use different screen resolutions, in order to accurately determine the key points on the first signature handwriting, this application embodiment considers the impact of different resolutions on the position and number of key points, that is, the key points of the first signature handwriting are determined by multi-resolution analysis.

[0052] For example, the above S120 may include the following steps:

[0053] S1201. Under a preset resolution, determine the feature information of the sampling points, where the sampling points are the points obtained by the first electronic device sampling the first signature handwriting at a preset sampling rate.

[0054] S1202. Based on the feature information, determine the candidate key points from the sampling points;

[0055] S1203. Determine the first key point based on the correlation between the preset resolution and the number of candidate key points.

[0056] Specifically, in S1201, the preset resolution can be set according to actual needs, and multiple resolutions can be selected as the preset resolution.

[0057] The sampling point is a point obtained by sampling the first signature handwriting using a first electronic device at a preset sampling rate. The first electronic device can be the aforementioned interactive device including a touch screen. The feature information of the sampling point may include, but is not limited to, the curvature and the first angle of the sampling point, wherein the first angle is the angle formed by the line connecting the sampling point and the adjacent sampling point.

[0058] In this way, feature information corresponding to the sampling point can be obtained at each preset resolution.

[0059] In S1202, the candidate key points are the key points of the first signature handwriting initially determined based on the feature information of the sampling points at a preset resolution.

[0060] For example, when the feature information includes the curvature of the sampling points, sampling points whose curvature meets preset conditions can be identified as candidate key points.

[0061] The preset conditions can be sampling points with abrupt changes in curvature, such as sampling points with a sudden increase or decrease in curvature, which can be set according to needs.

[0062] For example, if the feature information includes the angle formed by the line connecting the first sampling point and the adjacent sampling point, the first sampling point with an angle smaller than a preset angle can be determined as a candidate key point.

[0063] The preset angle can be set according to actual needs, for example, it can be 90 degrees.

[0064] In this embodiment of the application, candidate key points are determined by utilizing the curvature of points or the angle formed by connecting the current sampling point with adjacent sampling points at a preset resolution, which can improve the accuracy of candidate key points.

[0065] In S1203, the position and number of candidate key points can be determined at each preset resolution. As the preset resolution decreases, the number of candidate key points also gradually decreases. Therefore, a curve showing the relationship between the preset resolution and the number of candidate key points can be plotted.

[0066] The relationship curve reveals that at a certain preset resolution, the number of candidate key points suddenly decreases and then stabilizes. This indicates that at this preset resolution, the detailed information of the signature handwriting is not lost. This preset resolution can be designated as the critical resolution, and the candidate key point corresponding to this critical resolution can be identified as the first key point.

[0067] This application embodiment utilizes the relationship between preset resolution and the number of candidate key points to filter candidate key points, taking into account the impact of different resolutions on key points, and determines the candidate key point corresponding to the critical resolution as the first key point, thus ensuring the accuracy of the first key point.

[0068] In S130, the second key point is a key point referencing the signature handwriting, which is the signature handwriting of a real user. The reference signature handwriting can contain one or more key points. The number of the first and second key points can be the same or different.

[0069] Matching a first keypoint and a second keypoint can be based on their similarity. For example, if the similarity between a first keypoint and a second keypoint is greater than a preset similarity, then the first keypoint and the second keypoint can be considered to match. A first keypoint can match one or more second keypoints, and a second keypoint can also match one or more first keypoints.

[0070] For example, the similarity between the first keypoint and the second keypoint can be determined based on the distance between them, combined with a dynamic time warping algorithm. This allows us to determine whether the first keypoint and the second keypoint match, and the matched first keypoint and second keypoint are recorded as a keypoint matching pair. For instance, if the first keypoint A1 and the second keypoint B2 match, then the first keypoint A1 and the second keypoint B2 are called a keypoint matching pair. The principle of the dynamic time warping algorithm can be found in existing technologies and will not be elaborated here.

[0071] In S140, based on the key point matching pairs, the first and second handwriting segments that match can be determined. For example, if the first key point A1 matches the second key point B1, and the first key point A2 matches the second key point B2, then the handwriting segment corresponding to A1A2 and the handwriting segment corresponding to B1B2 are said to match. Here, the handwriting segment corresponding to A1A2 is the handwriting segment on the first signature handwriting, and the handwriting segment corresponding to B1B2 is the handwriting segment on the reference signature handwriting.

[0072] Considering that a first keypoint may match multiple second keypoints, or a second keypoint may match multiple first keypoints, the matched first and second handwriting segments obtained based on keypoint matching pairs may have a one-to-one, one-to-many, or many-to-many relationship. To facilitate subsequent calculations, one-to-many or many-to-one cases can be minimized. For example, when there are many one-to-many or many-to-one cases, the keypoint matching pairs can be further optimized. This application does not limit the specific optimization measures.

[0073] In S150, the first signature handwriting can be authenticated based on the distance between the first and second matching handwriting segments, thus determining whether the first signature handwriting and the reference signature handwriting are the signature handwriting of the same user.

[0074] If authentication is successful, it indicates that the first signature and the reference signature belong to the same user, and the user is allowed to log in to the first electronic device or an application on the first electronic device. If authentication fails, it indicates that the first signature and the reference signature do not belong to the same user, and the user is denied access to the first electronic device or an application on the first electronic device.

[0075] The distance between the first handwriting segment and the second handwriting segment can be determined based on the paragraph features of the first handwriting segment and the second handwriting segment. The paragraph features can be features that reflect the characteristics of the handwriting segment. For example, the paragraph features can include, but are not limited to, slant and speed.

[0076] Based on this, in some embodiments, prior to S150, the authentication method may further include the following steps:

[0077] The first paragraph features of the first handwriting segment are obtained. The first paragraph features include at least one of the following: the tilt angle of the first handwriting segment, the speed of the first handwriting segment, and the first angle corresponding to the fitting curve. The fitting curve is obtained based on the first and last endpoints of the first handwriting segment and a preset curve fitting method. The fitting curve includes at least the first and last endpoints of the first handwriting segment, as well as the first fitting point and the second fitting point.

[0078] Based on the first paragraph features of the first handwriting segment and the second paragraph features of the second handwriting segment, determine the distance between the matching first handwriting segment and the second handwriting segment.

[0079] The tilt angle can be determined based on the first and last endpoints of the first stroke segment. For example, the angle between the line connecting the first and last endpoints and the horizontal direction can be called the tilt angle of the first stroke segment.

[0080] The speed can be determined based on the arc length of the first handwriting segment and the sampling time. For example, the speed of the first handwriting segment = arc length of the first handwriting segment / sampling time.

[0081] The preset curve fitting method can be a Bézier curve fitting method. For example, a third-order Bézier fitting can be performed based on the beginning and end endpoints of the first handwriting segment to obtain a fitting curve. The first fitting point and the second fitting point are points obtained through curve fitting. The first fitting point and the second fitting point are located between the beginning and end endpoints of the first handwriting segment. Assuming that the fitting curve corresponds to point A (first point), point B (first fitting point), point C (second fitting point), and point D (end point) from left to right, the first angle can be the angle formed by the line connecting the first point and the first fitting point and the line connecting the first fitting point and the second fitting point, i.e., the angle formed by BA and BC, and the angle formed by the line connecting the first fitting point and the second fitting point and the line connecting the second fitting point and the end point, i.e., the angle formed by CB and CD.

[0082] The method for determining the characteristics of the second paragraph is similar to that for determining the characteristics of the first paragraph.

[0083] For example, feature values ​​of the first paragraph feature and the second paragraph feature can be determined respectively, and the Euclidean distance between the first handwriting segment and the second handwriting segment can be determined based on the feature values.

[0084] For example, the feature values ​​of the first segment include cosα1, sinα1, cosβ1, sinβ1, cosθ1, sinθ1, and v1, where α1 is the tilt angle of the first handwriting segment, β1 and θ1 are the first angles, and v1 is the velocity of the first handwriting segment. The feature values ​​of the second segment include cosα2, sinα2, cosβ2, sinβ2, cosθ2, cosθ2, and v2. Here, α2 is the tilt angle of the second stroke segment; β2 and θ2 are the second angles, i.e., the angles formed by the lines connecting the first and third fitting points of the second stroke segment and the lines connecting the third and fourth fitting points, and the angles formed by the lines connecting the third and fourth fitting points and the lines connecting the fourth fitting point and the tail point of the second stroke segment. The third and fourth fitting points are points obtained by fitting a third-order Bézier curve based on the first and tail endpoints of the second stroke segment. For example, the fitting curve corresponds from left to right to the first, third, fourth, and tail points of the second stroke segment, respectively. v2 is the velocity of the second stroke segment. Therefore, the distance between the first and second stroke segments is: d 1 / 2 .

[0085] d = (cosα1 - cosα2) 2 +(sinα1-sinα2) 2 +(cosβ1-cosβ2) 2 +(sinβ1-sinβ2) 2 +(cosθ1-cosθ2) 2 +(sinθ1-cosθ2) 2 +(v1-v2) 2

[0086] This application embodiment utilizes features such as the tilt angle and speed between matching paragraphs to determine the distance between matching paragraphs, fully considering the paragraph characteristics of the matching paragraphs. This allows for accurate determination of the distance between matching paragraphs, thereby improving the accuracy of the first signature handwriting authentication result.

[0087] Figure 2 This application provides a flowchart of another authentication method, which describes the matching process of the first key point and the second key point, as shown below:

[0088] S210, Obtain the first signature handwriting.

[0089] S220. Determine the first key point of the first signature handwriting through multi-resolution analysis.

[0090] S230. Determine the first shape support feature of the first key point based on the relative positional relationship between the first key points.

[0091] The first shape support feature is associated with the first signature handwriting.

[0092] S240. Determine the distance between the first key point and the second key point based on the first shape support feature and the second shape support feature.

[0093] Among them, the second shape support feature is the shape support feature of the second key point.

[0094] S250. Based on the distance and dynamic time warping algorithm, match the first keypoint and the second keypoint to obtain a keypoint matching pair.

[0095] S260. Based on the key point matching pairs, determine the first and second stroke segments to be matched.

[0096] S270. Authenticate the first signature handwriting based on the distance between the first and second matching handwriting segments.

[0097] S210-S220 and S260-S270 are the same as S110-S120 and S140-S150 in the above embodiments, and can be found in the above embodiments for details. The other steps are described below:

[0098] In S230, the first shape support feature is the shape support information of other key points in the first signature handwriting relative to the current key point, that is, the position information of other key points relative to the current key point.

[0099] Based on the relative positional relationship between the first key points, the first shape support feature of the first key points can be determined.

[0100] For example, the shape support features of the first key point can be determined in the following manner:

[0101] Using the third key point as the center and the distance between different first key points as the radius, draw N circles, where N is an integer greater than or equal to 1, and the third key point is any one of the first key points;

[0102] Centered on the third key point, divide the area into N circles according to a preset angle to obtain M regions, where M is an integer greater than 1;

[0103] Based on the relative positional relationship between the fourth key point and the third key point, the distribution information of the fourth key point in M ​​regions is determined, and the first vector corresponding to the third key point is obtained. The fourth key point is the key point other than the third key point among the first key points.

[0104] Arrange the first vectors of each third key point in sequence to obtain the first matrix, which serves as the first shape support feature of the first key point.

[0105] In this embodiment of the application, the third key point is any one of the first key points. For each of the first key points, the above-described process of determining the first shape support feature can be performed, so that for each first key point, the corresponding first shape support feature can be obtained.

[0106] The radius can be determined based on the distance between two first key points. For example, the minimum distance between two first key points can be determined as the first radius, and the second radius can be obtained based on the first radius. For example, the second radius is the second power of the first radius, the third radius is the cube of the first radius, and so on, to obtain the radii of N circles.

[0107] The preset angle can be set according to actual needs. For example, it can be set to 30 degrees, which divides the circle into 12 sectors, i.e., M=12.

[0108] The fourth key point is the key point other than the third key point among the first key points. The relative positional relationship between the fourth key point and the third key point can include the distance and angle of the fourth key point relative to the third key point.

[0109] For example, refer to Figure 3 With N=5 and a preset angle of 30 degrees, the five concentric circles can be divided into M=5*12=60 regions, corresponding to A1-A60 respectively. Assuming the third keypoint Pi falls within region A8, the distribution information of the fourth keypoint in these 60 regions can be determined based on the relative position of the fourth and third keypoints. For example, if region A1 contains one fourth keypoint, it can be denoted as 1; if region A2 contains five fourth keypoints, it can be denoted as 5. Following the order from A1 to A60, a 1*60 one-dimensional vector can be obtained, denoted as the first vector. Similarly, for each third keypoint, a 1*60 one-dimensional vector can be obtained. Arranging these one-dimensional vectors in order yields a P*60 matrix, also known as the first matrix, where P is the number of first keypoints. The first shape support of the first keypoint can be represented by the first matrix.

[0110] The second shape support feature of the second key point can be obtained in a similar way.

[0111] In this embodiment, multiple circles are drawn with each first key point as the center and the distance between different first key points as the radius. These circles are then divided into multiple regions at preset angles. Based on the positional information of other first key points relative to the current first key point, the distribution information of other first key points in each region is determined, thereby obtaining the vector of each first key point. Combining these vectors yields the shape support feature of the first key point. In other words, this embodiment considers the shape support information of other key points on the current key point, thus taking into account the influence of other key points on the current key point. This results in higher accuracy when determining the distance between key points of different signature handwritings based on the shape support features of the key points.

[0112] Considering the characteristics of handwritten signatures, in some embodiments, the distances and angles between different key points can be smoothed.

[0113] Taking the third keypoint Pi falling in region A8 as an example, assuming that the regions adjacent to region A8 are A7, A9, A3 and A14, after smoothing, region A8 can be recorded as 0.6, and regions A7, A9, A3 and A14 can be recorded as 0.1 respectively. The sum of each region is 1. Other keypoints are processed in a similar way.

[0114] In S240, the distance between the first key point and the second key point can be determined based on the shape support features of the first key point and the second key point.

[0115] For example, by multiplying the first matrix and the second matrix, the distance between each first keypoint and the second keypoint can be obtained.

[0116] In S250, the first and second keypoints can be determined by combining the distance between the first and second keypoints with the dynamic time warping algorithm, thus obtaining a keypoint matching pair.

[0117] Compared to the traditional method of determining Euclidean distance based on the positions of different key points, the embodiments of this application utilize the relative position information between different key points on the same signature handwriting to determine the shape support features of the key points. This considers more comprehensive information, thus improving the accuracy of the results when determining the distance between key points of different signature handwritings based on shape support features, and consequently improving the accuracy of key point matching pairs.

[0118] Figure 4 This application provides a flowchart of another authentication method, which describes the authentication process of the first signature handwriting as follows:

[0119] S410, Obtain the first signature handwriting.

[0120] S420. The first key point of the first signature handwriting is determined by multi-resolution analysis.

[0121] S430. Perform keypoint matching on the first keypoint and the second keypoint to obtain keypoint matching pairs.

[0122] S440. Based on the key point matching pairs, determine the first and second stroke segments to be matched.

[0123] S450. Determine the mean and variance of the distance based on the distance between the first and second matched handwriting segments.

[0124] S460. Based on the mean and variance of the distance, determine the first probability that the first handwriting segment and the second handwriting segment belong to the same user.

[0125] S470. Based on the first probability of each first handwriting segment, determine the second probability that the first signature handwriting and the reference signature handwriting belong to the same user.

[0126] S480. Based on the second probability, authenticate the first signature handwriting.

[0127] The processes S410-S440 are the same as those S110-S140, and can be found in the description of S110-S140. The other steps are explained below:

[0128] In S450, the distance mean and distance variance can be determined based on the mean formula and variance formula.

[0129] In S460, by inputting the mean and variance into the probability model, the first probability that the first and second handwriting segments belong to the same user can be obtained.

[0130] For example, the probability model can be a Gaussian model. Before practical application, it can be trained using real signatures of different users. This application does not limit the specific training process.

[0131] In S470, after the probability of each first handwriting segment is determined, the probabilities of each first handwriting segment are integrated to obtain the probability that the entire signature handwriting, i.e. the first signature handwriting, is a genuine signature handwriting. The probability that the first signature handwriting is a genuine signature handwriting is also the probability that the first signature handwriting and the reference signature handwriting belong to the same user, i.e., the second probability.

[0132] For example, the average probability of each first stroke segment can be used as the second probability.

[0133] Considering that the arc length of the first stroke segment accounts for a certain proportion of the entire signature stroke, in some embodiments, the second probability can also be determined in the following way:

[0134] The length weight of the first handwriting segment is determined based on the arc length of the first handwriting segment and the arc length of the first signature.

[0135] Based on the weighted sum of the length weight and the first probability, a second probability is determined that the first signature handwriting and the reference signature handwriting belong to the same user.

[0136] The arc length of the first handwriting segment can be determined based on the arc length between each sampling point. That is, the arc length between adjacent sampling points can be determined separately, and the arc length between each sampling point can be accumulated to obtain the arc length of the first handwriting segment.

[0137] The arc length of the first signature stroke can be determined based on the arc length of each segment of the first stroke.

[0138] The length weight of the first handwriting segment can be determined based on the arc length of the first handwriting segment and the arc length of the first signature. For example, the length weight of the first handwriting segment = the arc length of the first handwriting segment / the arc length of the first signature.

[0139] The second probability that the first signature and the reference signature belong to the same user can be obtained by weighting and summing the first probability and length weight of each first handwriting segment.

[0140] In determining the second probability of a first signature handwriting based on the first probability of each first handwriting segment, the embodiments of this application consider the length weight of each first handwriting segment, which can improve the accuracy of the second probability.

[0141] In S480, the first signature handwriting can be authenticated based on the second probability. For example, when the second probability is greater than a preset probability threshold, the first signature handwriting authentication is successful, that is, the user is allowed to log in based on the first signature handwriting; otherwise, the first signature handwriting authentication fails, and the user is refused to log in.

[0142] In practical applications, there may be multiple reference signature handwritings. Based on this, in some embodiments, the second probability that the first signature handwriting and each reference signature handwriting belong to the same user can be determined. Based on each second probability, the probability that the first signature handwriting is the user's real signature handwriting can be finally determined.

[0143] For example, the minimum probability and the maximum probability can be determined from a plurality of second probabilities, and the mean probability can be determined based on the plurality of second probabilities. Based on the minimum probability, the maximum probability and the mean probability, a voting mechanism is used to determine the final probability that the first signature handwriting is a genuine signature handwriting, and the first signature handwriting is authenticated based on the final probability.

[0144] In this embodiment of the application, when there are multiple reference signature handwritings, the probability that the first signature handwriting and each reference signature handwriting belong to the same user can be determined separately. Then, based on each probability, the probability that the first signature handwriting is a genuine signature handwriting is finally determined. In this way, different writing habits of the same user are taken into account, and the accuracy of the authentication results is improved.

[0145] Based on the same inventive concept, this application also provides an identity authentication device, which is described below in conjunction with... Figure 5 The identity authentication device provided in the embodiments of this application will be described in detail.

[0146] Figure 5 This is a structural diagram of an identity authentication device provided in an embodiment of this application.

[0147] like Figure 5 As shown, the identity authentication device may include an acquisition module 510, a determination module 520, a matching module 530, and an authentication module 540;

[0148] Module 510 is used to acquire the first signature handwriting.

[0149] The determination module 520 is used to determine the first key point of the first signature handwriting through multi-resolution analysis;

[0150] The matching module 530 is used to perform key point matching on the first key point and the second key point to obtain a key point matching pair, wherein the second key point is a key point for reference signature handwriting.

[0151] The determination module 520 is also used to determine the first handwriting segment and the second handwriting segment that are matched based on the key point matching pair. The first handwriting segment is the handwriting segment formed by the first key point in the first signature handwriting, and the second handwriting segment is the handwriting segment formed by the second key point in the reference signature handwriting.

[0152] The authentication module 540 is used to authenticate the first signature handwriting based on the distance between the matching first and second handwriting segments.

[0153] The identity authentication device provided in this application acquires a first signature handwriting, determines a first key point of the first signature handwriting through multi-resolution analysis, performs key point matching on the first key point and a second key point to obtain a key point matching pair, and uses the second key point as a key point of the reference signature handwriting; determines a matching first handwriting segment and a matching second handwriting segment based on the key point matching pair; and authenticates the first signature handwriting based on the distance between the matching first handwriting segment and the second handwriting segment. Compared with traditional schemes that use usernames and passwords to authenticate user identities, this application embodiment uses signature handwriting for identity authentication, which can effectively avoid adverse consequences caused by the leakage of usernames and passwords. At the same time, by using multi-resolution analysis to determine the key points of the first signature handwriting, the influence of different resolutions on the key points is considered, improving the accuracy of the key points. Thus, when authenticating the first signature handwriting based on key points in subsequent processes, the accuracy of the authentication result can be improved, thereby enhancing the security of identity authentication.

[0154] In some embodiments, the determining module 520 is specifically used for:

[0155] At a preset resolution, the feature information of the sampling points is determined, wherein the sampling points are points obtained by the first electronic device sampling the first signature handwriting at a preset sampling rate;

[0156] Based on the feature information, candidate key points are determined from the sampling points;

[0157] The first key point is determined based on the correlation between the preset resolution and the number of candidate key points.

[0158] In some embodiments, the feature information includes the curvature of the sampling points;

[0159] Module 520 is specifically used for:

[0160] Sampling points whose curvature meets preset conditions are identified as candidate key points.

[0161] In some embodiments, the feature information includes the angle formed by the line connecting the first sampling point and the adjacent sampling points;

[0162] Module 520 is specifically used for:

[0163] The first sampling point with an angle smaller than the preset angle is determined as a candidate key point.

[0164] In some embodiments, the matching module 530 is specifically used for:

[0165] Based on the relative positional relationship between the first key points, the first shape support feature of the first key point is determined, and the first shape support feature is associated with the first signature handwriting.

[0166] The distance between the first key point and the second key point is determined based on the first shape support feature and the second shape support feature, wherein the second shape support feature is the shape support feature of the second key point;

[0167] Based on the distance and dynamic time warping algorithm, the first keypoint and the second keypoint are matched to obtain keypoint matching pairs.

[0168] In some embodiments, the matching module 530 is specifically used for:

[0169] Using the third key point as the center and the distance between different first key points as the radius, draw N circles, where N is an integer greater than or equal to 1, and the third key point is any one of the first key points;

[0170] Centered on the third key point, divide the area into N circles according to a preset angle to obtain M regions, where M is an integer greater than 1;

[0171] Based on the relative positional relationship between the fourth key point and the third key point, the distribution information of the fourth key point in M ​​regions is determined, and the first vector corresponding to the third key point is obtained. The fourth key point is the key point other than the third key point among the first key points.

[0172] Arrange the first vectors of each third key point in sequence to obtain the first matrix, which serves as the first shape support feature of the first key point.

[0173] In some embodiments, the acquisition module 510 is further configured to acquire a first segment feature of the first handwriting segment before the authentication module 540 authenticates the first signature handwriting based on the distance between the matched first handwriting segment and the second handwriting segment. The first segment feature includes at least one of the following: the tilt angle of the first handwriting segment, the speed of the first handwriting segment, and the first angle corresponding to the fitting curve. The fitting curve is obtained based on the first and last endpoints of the first handwriting segment and a preset curve fitting method. The fitting curve includes at least the first and last endpoints of the first handwriting segment, the first fitting point, and the second fitting point.

[0174] The determining module 520 is further configured to determine the distance between the matching first handwriting segment and the second handwriting segment based on the first paragraph features of the first handwriting segment and the second paragraph features of the second handwriting segment.

[0175] In some embodiments, the authentication module 540 is specifically used for:

[0176] Determine the mean and variance of the distance based on the distance between the first and second matched handwriting segments;

[0177] Based on the mean and variance of the distance, determine the first probability that the first handwriting segment and the second handwriting segment belong to the same user;

[0178] Based on the first probability of each first handwriting segment, determine the second probability that the first signature handwriting and the reference signature handwriting belong to the same user;

[0179] Based on the second probability, the first signature handwriting is authenticated.

[0180] In some embodiments, the authentication module 540 is specifically used for:

[0181] The length weight of the first handwriting segment is determined based on the arc length of the first handwriting segment and the arc length of the first signature.

[0182] Based on the weighted sum of the length weight and the first probability, a second probability is determined that the first signature handwriting and the reference signature handwriting belong to the same user.

[0183] Figure 5 Each module in the illustrated device has the ability to implement Figures 1-4 The functions of each step and the corresponding technical effects are described in detail here for the sake of brevity.

[0184] Based on the same inventive concept, embodiments of this application also provide an electronic device, such as an interactive flat panel, tablet computer, laptop computer, handheld computer, etc. The following describes... Figure 6 The electronic devices provided in the embodiments of this application will be described in detail.

[0185] like Figure 6 As shown, the electronic device may include a processor 610, a memory 620 for storing computer program instructions, and a touch screen 630.

[0186] The processor 610 may include a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits that may be configured to implement the embodiments of this application.

[0187] Memory 620 may include mass storage for data or instructions. For example, and not limitingly, memory 620 may include a hard disk drive (HDD), a floppy disk drive, flash memory, optical disk, magneto-optical disk, magnetic tape, or a Universal Serial Bus (USB) drive, or a combination of two or more of these. In one instance, memory 620 may include removable or non-removable (or fixed) media, or memory 620 may be non-volatile solid-state memory. In one instance, memory 620 may be read-only memory (ROM). In one instance, the ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), an electrically rewritable ROM (EAROM), or flash memory, or a combination of two or more of these.

[0188] The touchscreen 630 can receive a first signature, which, exemplarily, can be a user's handwritten signature. Of course, the user can also perform other functions through the touchscreen 630, and this embodiment does not limit this functionality.

[0189] The processor 610 reads and executes computer program instructions stored in the memory 620 to achieve... Figures 1-4 The method in the illustrated embodiment achieves... Figures 1-4 The corresponding technical effects achieved by the methods in the illustrated embodiments are described briefly and will not be elaborated further here.

[0190] In one example, the electronic device may also include a communication interface 640 and a bus 650. Wherein, for example... Figure 6 As shown, the processor 610, memory 620, touch screen 630, and communication interface 640 are connected via bus 650 and complete communication with each other.

[0191] The communication interface 640 is mainly used to realize communication between various modules, devices and / or equipment in the embodiments of this application.

[0192] Bus 650 includes hardware, software, or both, that couples the components of an electronic device together. For example, and not as a limitation, bus 650 may include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an Infinite Bandwidth Interconnect, a Low Pin Count (LPC) bus, a memory bus, a Microchannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local (VLB) bus, or other suitable buses, or combinations of two or more of these. Where appropriate, bus 650 may include one or more buses. Although specific buses are described and illustrated in embodiments of this application, any suitable bus or interconnect is contemplated herein.

[0193] After acquiring the first signature handwriting, the electronic device can execute the identity authentication method in this application embodiment, thereby achieving a combination of... Figures 1-4 The described authentication method and Figure 5 The described identity authentication device.

[0194] Furthermore, in conjunction with the authentication methods described in the above embodiments, this application embodiment can provide a computer storage medium for implementation. The computer storage medium stores computer program instructions; when these computer program instructions are executed by a processor, they implement any of the authentication methods described in the above embodiments.

[0195] It should be clarified that this application is not limited to the specific configurations and processes described above and shown in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of this application is not limited to the specific steps described and shown. Those skilled in the art can make various changes, modifications, and additions, or change the order of steps, after understanding the spirit of this application.

[0196] The functional blocks shown in the above-described block diagram can be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, they can be, for example, electronic circuits, application-specific integrated circuits (ASICs), appropriate firmware, plug-ins, function cards, etc. When implemented in software, the elements of this application are programs or code segments used to perform the required tasks. Programs or code segments can be stored on a machine-readable medium or transmitted over a transmission medium or communication link via data signals carried on a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, radio frequency (RF) links, etc. Code segments can be downloaded via computer networks such as the Internet, intranets, etc.

[0197] It should also be noted that the exemplary embodiments mentioned in this application describe methods or systems based on a series of steps or apparatus. However, this application is not limited to the order of the above steps; that is, the steps can be performed in the order mentioned in the embodiments, or in a different order, or several steps can be performed simultaneously.

[0198] The aspects of embodiments of this application have been described above with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It should be understood that each block in the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, 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, or other programmable data processing apparatus to create a machine such that these instructions, executable via the processor of the computer or other programmable data processing apparatus, enable the implementation of the functions / actions specified in one or more blocks of the flowchart illustrations and / or block diagrams. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field-programmable logic circuit. It is also understood that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can also be implemented by dedicated hardware performing the specified functions or actions, or can be implemented by a combination of dedicated hardware and computer instructions.

[0199] The above description is merely a specific implementation of this application. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, modules, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here. It should be understood that the protection scope of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the protection scope of this application.

Claims

1. An identity authentication method, characterized in that, include: Obtain the first signature handwriting; The first key point of the first signature handwriting was determined by multi-resolution analysis. The first key point and the second key point are matched to obtain a key point matching pair, and the second key point is the key point of the reference signature handwriting. Based on the key point matching pair, a first handwriting segment and a second handwriting segment are determined to match. The first handwriting segment is the handwriting segment formed by the first key point in the first signature handwriting, and the second handwriting segment is the handwriting segment formed by the second key point in the reference signature handwriting. The first signature handwriting is authenticated based on the distance between the first and second matching handwriting segments. The method of determining the first key point of the first signature handwriting through multi-resolution analysis includes: At a preset resolution, the feature information of the sampling points is determined, wherein the sampling points are points obtained by the first electronic device sampling the first signature handwriting at a preset sampling rate; Based on the feature information, candidate key points are determined from the sampling points; Plot the relationship curve between the preset resolution and the number of candidate key points. Determine the preset resolution corresponding to the sudden decrease and stabilization of the number of candidate key points in the relationship curve as the critical resolution. Determine the candidate key point corresponding to the critical resolution as the first key point.

2. The method according to claim 1, characterized in that, The feature information includes the curvature of the sampling points; The step of determining candidate key points from the sampling points based on the feature information includes: Sampling points whose curvature meets preset conditions are identified as candidate key points.

3. The method according to claim 1, characterized in that, The feature information includes the angle formed by the line connecting the first sampling point and the adjacent sampling points; The step of determining candidate key points from the sampling points based on the feature information includes: The first sampling point with an angle smaller than the preset angle is determined as a candidate key point.

4. The method according to claim 1, characterized in that, The step of performing keypoint matching on the first keypoint and the second keypoint to obtain keypoint matching pairs includes: Based on the relative positional relationship between the first key points, a first shape support feature of the first key points is determined, and the first shape support feature is associated with the first signature handwriting. The distance between the first key point and the second key point is determined based on the first shape support feature and the second shape support feature, wherein the second shape support feature is the shape support feature of the second key point; Based on the distance and dynamic time warping algorithm, the first keypoint and the second keypoint are matched to obtain a keypoint matching pair.

5. The method according to claim 4, characterized in that, The step of determining the first shape support feature of the first key point based on the relative positional relationship between the first key points includes: Using the third key point as the center and the distance between different first key points as the radius, draw N circles, where N is an integer greater than or equal to 1, and the third key point is any one of the first key points; Centered on the third key point, divide the N circles according to a preset angle to obtain M regions, where M is an integer greater than 1; Based on the relative positional relationship between the fourth key point and the third key point, the distribution information of the fourth key point in the M regions is determined, and a first vector corresponding to the third key point is obtained. The fourth key point is a key point other than the third key point among the first key points. Arrange the first vectors of each of the third key points in sequence to obtain a first matrix, which serves as the first shape support feature of the first key points.

6. The method according to claim 1, characterized in that, Before authenticating the first signature handwriting based on the distance between the matched first and second handwriting segments, the method further includes: The first paragraph feature of the first handwriting segment is obtained, and the first paragraph feature includes at least one of the following: the tilt angle of the first handwriting segment, the speed of the first handwriting segment, and the first angle corresponding to the fitting curve. The fitting curve is obtained based on the first and last endpoints of the first handwriting segment and a preset curve fitting method. The fitting curve includes at least the first and last endpoints of the first handwriting segment, the first fitting point, and the second fitting point. The distance between the matched first and second handwriting segments is determined based on the first paragraph features of the first handwriting segment and the second paragraph features of the second handwriting segment.

7. The method according to any one of claims 1-6, characterized in that, The authentication of the first signature handwriting based on the distance between the matched first and second handwriting segments includes: Determine the mean and variance of the distance based on the distance between the first and second matched handwriting segments; Based on the mean and variance of the distance, determine the first probability that the first handwriting segment and the second handwriting segment belong to the same user; Based on the first probability of each of the first handwriting segments, a second probability is determined that the first signature handwriting and the reference signature handwriting belong to the same user; The first signature handwriting is authenticated based on the second probability.

8. The method according to claim 7, characterized in that, The step of determining the second probability that the first signature handwriting and the reference signature handwriting belong to the same user based on the first probability of each of the first handwriting segments includes: The length weight of the first handwriting segment is determined based on the arc length of the first handwriting segment and the arc length of the first signature. Based on the weighted sum of the length weight and the first probability, a second probability is determined that the first signature handwriting and the reference signature handwriting belong to the same user.

9. An identity authentication device, characterized in that, It includes an acquisition module, a determination module, a matching module, and an authentication module; The acquisition module is used to acquire the first signature handwriting; The determining module is used to determine the first key point of the first signature handwriting through multi-resolution analysis; The determining module is used to determine the first key point of the first signature handwriting through multi-resolution analysis, including: At a preset resolution, the feature information of the sampling points is determined, wherein the sampling points are points obtained by the first electronic device sampling the first signature handwriting at a preset sampling rate; Based on the feature information, candidate key points are determined from the sampling points; Plot the relationship curve between the preset resolution and the number of candidate key points. Determine the preset resolution corresponding to the sudden decrease and stabilization of the number of candidate key points in the relationship curve as the critical resolution. Determine the candidate key point corresponding to the critical resolution as the first key point. The matching module is used to perform key point matching on the first key point and the second key point to obtain a key point matching pair, wherein the second key point is a key point for reference signature handwriting. The determining module is further configured to determine a matching first handwriting segment and a matching second handwriting segment based on the key point matching pair, wherein the first handwriting segment is a handwriting segment formed by a first key point in the first signature handwriting, and the second handwriting segment is a handwriting segment formed by a second key point in the reference signature handwriting. The authentication module is used to authenticate the first signature handwriting based on the distance between the matched first and second handwriting segments.

10. An electronic device, characterized in that, include: processor; Memory is used to store computer program instructions; A touchscreen is used to receive the first signature handwriting. When the computer program instructions are executed by the processor, the method as described in any one of claims 1-7 is implemented.

11. A computer-readable storage medium storing computer program instructions thereon, characterized in that, When the computer program instructions are executed by the processor, the method as described in any one of claims 1-7 is implemented.

Images