A signature verification method, apparatus, device, storage medium, and product.

Abstract

This invention discloses a signature verification method, apparatus, device, storage medium, and product. The invention relates to the field of image recognition technology. The method includes: acquiring the actual individual signature features of at least two actual signature images corresponding to a target object; merging the actual individual signature features using a preset merging strategy to obtain the actual merged signature features corresponding to the target object; determining the number of successful signature matches based on the comparison result between the actual merged signature features and the benchmark merged signature features matching the target object; and determining the signature verification result of the target object based on the number of successful signature matches and pre-configured signature verification rules. The technical solution of this invention solves the technical problems of high verification costs, slow response speed, and high error rates caused by the need for manual comparison of multiple signatures one by one in the prior art, reducing verification costs and improving comparison efficiency and accuracy.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of image recognition technology, and in particular to a signature verification method, apparatus, device, storage medium and product. Background Technology

[0002] A signature, as a unique behavioral characteristic of a user, is one of the traditional ways to represent personal identity, especially widely used in the financial industry as a recognized method of identity authentication for business transactions and accounting. In the corporate banking sector, for the sake of fund security, multiple signatures are often required to authorize transactions before they can be processed. Existing methods for comparing multiple handwritten signatures are relatively outdated, mostly requiring the collection of each customer's signature on-site, retrieval of the customer's pre-registered signature image information, manual comparison of on-site signatures with pre-registered signatures, and finally determination of whether all on-site signatures meet the authorization rules. This process involves numerous steps, is inefficient, and prone to errors. The more signatures that need to be compared, the greater the workload and the higher the error rate. Summary of the Invention

[0003] This invention provides a signature verification method, apparatus, device, storage medium, and product to solve the technical problems of high cost, slow response speed, and high error rate caused by the need for manual comparison of multiple signatures one by one in the prior art.

[0004] In a first aspect, embodiments of the present invention provide a signature verification method, the method comprising:

[0005] Obtain the actual individual signature features of each target's actual signature image corresponding to the target object;

[0006] The actual individual signature features are merged using a preset merging strategy to obtain the actual merged signature features corresponding to the target object;

[0007] The number of successful signature matches is determined based on the comparison results between the actual merged signature features and the benchmark merged signature features that match the target object.

[0008] The signature verification result of the target object is determined based on the number of successful signature matches and the pre-configured signature verification rules.

[0009] Secondly, embodiments of the present invention also provide a signature verification device, the device comprising:

[0010] The first acquisition module is used to acquire the actual individual signature features of each target actual signature image corresponding to the target object;

[0011] The first merging module is used to merge the actual individual signature features using a preset merging strategy to obtain the actual merged signature features corresponding to the target object.

[0012] The first determining module is used to determine the number of successful signature matches based on the comparison result of the actual merged signature features and the benchmark merged signature features that match the target object.

[0013] The second determining module is used to determine the signature verification result of the target object based on the number of successful signature matches and the pre-configured signature verification rules.

[0014] Thirdly, embodiments of the present invention also provide an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the signature verification method as described in any of the embodiments of the present invention.

[0015] Fourthly, embodiments of the present invention also provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the signature verification method as described in any of the embodiments of the present invention.

[0016] Fifthly, embodiments of the present invention also provide a computer program product, including a computer program that, when executed by a processor, implements the signature verification method as described in any of the embodiments of the present invention.

[0017] The technical solution of this embodiment merges the actual individual signature features corresponding to multiple target actual signature images and regenerates a merged actual signature feature. This allows multiple actual signature images to be verified in one step to complete identity verification. The actual merged signature feature is compared with the benchmark merged signature feature to obtain the number of successful signature matches. When the number of successful signature matches reaches the signature verification rule, the signature verification of the target object is determined to be successful. This solves the technical problems of high cost, slow response speed and high error rate caused by the need for manual comparison of multiple signatures one by one in the prior art. It reduces the verification cost and improves the comparison efficiency and accuracy. Attached Figure Description

[0018] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a flowchart of a signature verification method provided in an embodiment of the present invention;

[0020] Figure 2This is a flowchart of another signature verification method provided in an embodiment of the present invention;

[0021] Figure 3 This is a flowchart of another signature verification method provided in an embodiment of the present invention;

[0022] Figure 4 This is a schematic diagram of a signature verification process provided by an embodiment of the present invention;

[0023] Figure 5 This is a flowchart of an automatic comparison of multiple signatures provided in an embodiment of the present invention;

[0024] Figure 6 This is a schematic diagram of the structure of a signature verification device provided in an embodiment of the present invention;

[0025] Figure 7 This is a structural block diagram of a signature verification electronic device provided in an embodiment of the present invention. Detailed Implementation

[0026] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0027] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0028] The acquisition, storage, use, and processing of data in this application all comply with the relevant provisions of national laws and regulations.

[0029] In one embodiment, Figure 1This is a flowchart of a signature verification method provided by an embodiment of the present invention. This embodiment is applicable to situations in corporate business scenarios where multiple users' signatures need to be verified. This method can be executed by a signature verification device, which can be implemented in hardware and / or software and can be configured in an electronic device. Figure 1 As shown, the method includes:

[0030] S110. Obtain the actual individual signature features of at least two actual signature images corresponding to the target object.

[0031] It should be noted that in corporate banking scenarios, multiple user signatures are required to complete the transaction. In this embodiment, the target object refers to an account that has activated corporate banking services. When this target object conducts corporate banking transactions, multiple user signatures are required to complete the transaction. The target actual signature image refers to a processed handwritten signature image captured during the on-site corporate banking operation; the actual individual signature feature is used to characterize the signature feature information corresponding to the signature image captured by a user corresponding to the target object in the actual corporate banking scenario. In this embodiment, the actual individual signature feature includes: actual individual handwriting feature and actual individual pressure feature, wherein the actual individual handwriting feature characterizes the user's movement trajectory during the handwriting process; and the actual individual pressure feature characterizes the writing pressure applied during the handwriting process.

[0032] S120. The actual individual signature features are merged using a preset merging strategy to obtain the actual merged signature features corresponding to the target object.

[0033] Here, the actual merged signature feature refers to the merged signature feature obtained by merging multiple actual individual signature features. In the embodiment, the actual individual handwriting features can be represented by a matrix; the actual individual pressure features can be represented by a vector. The process of merging actual individual signature features using a preset merging strategy can be understood as merging the matrix used to represent the actual individual handwriting features and merging the vector used to represent the actual individual pressure features using a preset merging strategy, and using the merged matrix as the corresponding actual merged handwriting feature, and using the merged vector as the corresponding actual merged pressure feature.

[0034] S130. Determine the number of successful signature matches based on the comparison results of the benchmark merged signature features that match the actual merged signature features and the target object.

[0035] The benchmark merged signature feature refers to the signature feature obtained by merging multiple benchmark individual signature features corresponding to the target object. In this embodiment, after obtaining all authorized users corresponding to the target object, a benchmark signature image of each authorized user is acquired, and the benchmark individual signature feature corresponding to each benchmark signature image is obtained. All benchmark individual signature features are then merged to obtain the corresponding benchmark merged signature feature. This can be understood as the number of authorized users corresponding to the benchmark merged signature feature being greater than or equal to the number of authorized users corresponding to the actual merged signature feature. In actual operation, the number of authorized users corresponding to the target object can be up to 10, but in actual operation, the number of actual target signature images acquired on-site can be less than 10, and the corresponding number of authorized users corresponding to the actual merged signature feature can be less than 10.

[0036] The number of successful signature matches refers to the number of authorized users corresponding to the actual merged signature feature and the authorized users corresponding to the benchmark merged signature feature who are the same. In this embodiment, the number of successful signature matches can be determined based on the similarity between the actual merged signature feature and the benchmark merged signature feature.

[0037] S140. Determine the signature verification result of the target object based on the number of successful signature matches and the pre-configured signature verification rules.

[0038] The signature verification rule is used to characterize the threshold for successful signature matching. This can be understood as follows: if the number of successful signature matches reaches the threshold, the signature verification of the target object passes; conversely, if the number of successful signature matches does not reach the threshold, the signature verification of the target object fails.

[0039] The technical solution of this embodiment merges the actual individual signature features corresponding to multiple target actual signature images and regenerates a merged actual signature feature. This allows multiple actual signature images to be verified in one step to complete identity verification. The actual merged signature feature is compared with the benchmark merged signature feature to obtain the number of successful signature matches. When the number of successful signature matches reaches the signature verification rule, the signature verification of the target object is determined to be successful. This solves the technical problems of high cost, slow response speed and high error rate caused by the need for manual comparison of multiple signatures one by one in the prior art. It reduces the verification cost and improves the comparison efficiency and accuracy.

[0040] In one embodiment, Figure 2 This is a flowchart of another signature verification method provided by an embodiment of the present invention. This embodiment describes the process of obtaining the actual signature image of the target based on the above embodiments. Figure 2 As shown, the method includes:

[0041] S210. Obtain at least two original actual signature images corresponding to the target object.

[0042] The original actual signature image refers to the unprocessed handwritten signature image captured during on-site corporate banking operations. In corporate banking scenarios, multiple users need to authorize simultaneously to process the transaction. An image capture device can be used to capture the handwritten signatures of each authorized user corresponding to the target object, serving as the corresponding original actual signature image.

[0043] S220. Normalize each original actual signature image to obtain the corresponding target actual signature image.

[0044] In practice, the size of each authorized user's handwritten signature is different. In order to facilitate the extraction of signature features, each original actual signature image can be normalized so that the signature image of each authorized user is controlled within a certain range, thus obtaining the corresponding target actual signature image.

[0045] In one embodiment, S220 includes S2201-S2202:

[0046] S2201. Obtain the initial image size for each original actual signature image.

[0047] Here, the initial image size refers to the original size of each original actual signature image before any scaling operations such as shrinking or enlarging are performed. In this embodiment, the initial image size of each original actual signature image can be obtained directly through existing API functions or size acquisition functions.

[0048] S2202. When the initial image size reaches the image size threshold, normalize each original actual signature image to obtain the target actual signature image of the target image size.

[0049] In this embodiment, if the initial image size exceeds an image size threshold, the original actual signature image is too large. To facilitate subsequent signature feature extraction, the original actual signature image can be normalized to obtain a target actual signature image of the target size. In practice, a size reduction function can be directly used to reduce the initial size of the original actual signature image to obtain the corresponding target actual signature image.

[0050] S230. Obtain the actual individual signature features of at least two actual signature images corresponding to the target object.

[0051] S240. The actual individual signature features are merged using a preset merging strategy to obtain the actual merged signature features corresponding to the target object.

[0052] S250. Determine the number of successful signature matches based on the comparison results of the benchmark merged signature features that match the actual merged signature features and the target object.

[0053] S260. Determine the signature verification result of the target object based on the number of successful signature matches and pre-configured signature verification rules.

[0054] The technical solution of this embodiment, based on the above embodiment, normalizes the original actual signature image to obtain a target actual signature image within the target image size range, which facilitates the subsequent extraction of actual signature features from the actual signature image and improves feature extraction efficiency.

[0055] In one embodiment, Figure 3 This is a flowchart of another signature verification method provided by an embodiment of the present invention. This embodiment, based on the above embodiments, describes the process of obtaining actual individual signature features, the process of merging actual merged signature features, the process of determining the number of successfully matched signatures, and the process of determining the signature verification result. Figure 3 As shown, this embodiment includes the following steps:

[0056] S310. Obtain the pixel coordinate information of at least two actual signature images of the target object.

[0057] The pixel coordinate information can be represented using the RGB values ​​of the actual target signature image. In this embodiment, the RGB values ​​of each actual target signature image are directly obtained using existing technology as the corresponding pixel coordinate information.

[0058] S320. Determine the initial matrix for characterizing individual handwriting features based on pixel coordinate information.

[0059] In this embodiment, based on empirical mode decomposition and singular value decomposition, the authentic mode function components corresponding to the pixel coordinate information of each target actual signature image are obtained. An initial matrix is ​​created based on the authentic mode function components, and the initial matrix is ​​used to characterize the individual handwriting features corresponding to the target actual signature image.

[0060] S330. Perform singular value decomposition on the initial matrix to obtain the energy value eigenvector used to characterize the individual strength characteristics.

[0061] In this embodiment, singular value decomposition is performed on the initial matrix to obtain the corresponding energy value feature vector, and this energy value feature vector is used to characterize the individual strength characteristics.

[0062] S340. Overlay the initial matrix corresponding to the handwriting features of each actual individual to obtain the actual merged handwriting features corresponding to the target object.

[0063] In this embodiment, the initial matrix used to characterize the handwriting features of each actual individual is superimposed to obtain a new matrix, and this new matrix is ​​used to characterize the actual merged handwriting features corresponding to the target object.

[0064] S350. Superimpose the energy value feature vectors corresponding to the actual individual force characteristics to obtain the actual combined force characteristics of the target object.

[0065] In this embodiment, the energy value feature vectors used to characterize the force characteristics of each actual individual are superimposed to obtain a new energy value feature vector, and this new energy value feature vector is used to characterize the actual combined force characteristics of the target object.

[0066] S360. The optimal signature path between the actual merged signature feature and the benchmark merged signature feature is determined by a preset path matching algorithm.

[0067] The preset path matching algorithm can be a time-calibrated path matching algorithm, which is based on dynamic programming. Its basic principle is to align the initial matrix representing handwriting features or the energy value feature vector representing intensity features. Then, it expands the two initial matrices representing the actual merged handwriting features and the reference merged handwriting features, or the two energy value feature vectors representing the actual merged intensity features and the reference merged intensity features, into a matrix of length N*M, where N and M represent the lengths of the two time series. It defines a two-dimensional dynamic programming array D[N][M], where D[i][j] represents the minimum distance required to map the first i elements of the first time series to the first j elements of the second time series. Then, it searches for an optimal path in the matrix such that each time point on this path is unique, and all time points on this path have appeared before or after the original time series. It then recursively calculates the value of D[i][j] until the optimal path is found. For example, the preset path matching algorithm can be a dynamic time warping (DTW) algorithm.

[0068] S370. Determine the distance between the optimal signature path and the actual merged signature feature and the benchmark merged signature feature, as the corresponding actual signature distance and benchmark signature distance.

[0069] In this embodiment, the distance between the optimal signature path and the actual merged signature feature (i.e., on-site signature) is calculated using a preset path matching algorithm, and is used as the corresponding actual signature distance; and the distance between the optimal signature path and the benchmark merged signature feature (i.e., reserved signature) is calculated using a preset path matching algorithm, and is used as the corresponding benchmark signature distance.

[0070] S380. Obtain the pre-configured similarity mapping table.

[0071] The similarity mapping table is used to represent the mapping relationship between similarity and the number of successful signature matches. In this embodiment, the similarity mapping table stores the mapping relationship between the number of successful signature matches and the similarity. For example, when the number of successful signature matches is 4, the similarity reaches 30%; and when the number of successful signature matches is 3, the similarity reaches 23%.

[0072] S390. Determine the number of successful signature matches based on the actual signature distance and the baseline signature distance.

[0073] In one embodiment, S390 includes: S3901-S3902:

[0074] S3901. Determine the actual similarity between the actual merged signature feature and the benchmark merged signature feature based on the actual signature distance and the benchmark signature distance.

[0075] In this embodiment, the actual similarity between the actual merged signature feature and the benchmark merged signature feature is determined based on the relative distance difference between the actual signature distance and the benchmark signature distance. This can be understood as follows: the larger the relative distance difference between the actual signature distance and the benchmark signature distance, the lower the actual similarity between the actual merged signature feature and the benchmark merged signature feature; conversely, the smaller the relative distance difference between the actual signature distance and the benchmark signature distance, the higher the actual similarity between the actual merged signature feature and the benchmark merged signature feature.

[0076] S3902. Determine the number of successful signature matches based on the actual similarity and the similarity mapping table.

[0077] In this embodiment, a similarity score that is closest to and less than the actual similarity score is found in a pre-configured similarity mapping table. The number of successful signature matches for the target object is determined based on the number of matches corresponding to this closest but less than actual similarity score. For example, assuming the actual similarity score is 'a', and the closest but less than 'a' similarity score found in the similarity mapping table is 'b', then the number of matches corresponding to 'b' in the similarity mapping table is 'c', and the number of successful signature matches for the target object is 'c'.

[0078] S3100. Determine the signature success matching threshold corresponding to the target object based on the signature verification rules.

[0079] The signature success matching threshold refers to the minimum number of successful signature matches required for the target object to pass verification. In this embodiment, the signature success matching threshold is directly proportional to the authorization level of the target object; that is, the higher the authorization level of the target object, the larger the corresponding signature success matching threshold. In this embodiment, the authorization level of the target object can be obtained from the signature verification rules, and the corresponding signature success matching threshold can be found based on the authorization level; alternatively, the signature success matching threshold corresponding to the target object can be directly obtained from the signature verification rules.

[0080] S3110. Determine the signature verification result of the target object based on the comparison result between the number of successful signature matches and the signature successful match threshold.

[0081] In this embodiment, if the number of successfully matched signatures reaches the threshold for successful signature matching, the signature verification result of the target object is "signature verification passed"; if the number of successfully matched signatures does not reach the threshold for successful signature matching, the signature verification result of the target object is "signature verification failed".

[0082] The technical solution of this embodiment, based on the above embodiments, obtains the actual individual handwriting features and actual individual strength features of each target actual signature image, and merges the actual individual handwriting features and actual individual strength features to obtain the corresponding actual merged signature features; then, a preset path matching algorithm is used to determine the optimal signature path between the actual merged signature features and the benchmark merged signature features; the distance between the optimal signature path and the actual merged signature features and the benchmark merged signature features is determined as the corresponding actual signature distance and benchmark signature distance; the number of successful signature matches is determined based on the actual signature distance and the benchmark signature distance, and when the number of successful signature matches reaches the successful signature matching threshold, the signature verification result of the target object is determined as successful signature verification. Thus, the identity verification of the target object can be completed by comparing multiple actual individual signature features at once, without having to compare each actual individual signature feature one by one. In addition to reducing verification costs and improving comparison speed, it also reduces the amount of data storage, thereby reducing memory occupation.

[0083] In one embodiment, the signature verification method further includes: obtaining the baseline individual signature features of each baseline individual signature image corresponding to the target object; merging the baseline individual signature features using a preset merging strategy to obtain the baseline merged signature features of the target object; encrypting the baseline merged signature features based on the encryption level of the target object; and storing the encrypted baseline merged signature features in a target storage path. In this embodiment, the merging process of the baseline individual signature features can refer to the merging process of actual individual signature features to obtain the corresponding baseline merged signature features; the specific merging process will not be elaborated here. In actual operation, the baseline merged signature features can be encrypted according to the encryption level of the public business corresponding to the target object, and each encrypted baseline merged signature feature can be stored in the target storage path.

[0084] In one embodiment, storing each encrypted benchmark merged signature feature in a target storage path includes: storing the benchmark merged signature feature corresponding to the target object and pre-configured signature verification rules in one of the individual feature files in the target storage path, thereby obtaining an object signature feature file matching the target object. The object signature feature file stores the benchmark merged signature feature and signature verification rules required for a target object to process a specific type of corporate business transaction. In this embodiment, one target object can correspond to multiple corporate business transactions, and correspondingly, one target object can correspond to multiple object signature feature files. By storing the benchmark merged signature feature and signature verification rules corresponding to a corporate business transaction type in one object signature feature file, errors in the signature verification rules and benchmark merged signature features used for signature verification can be avoided, and the search efficiency for signature verification rules and benchmark merged signature features is also improved.

[0085] In one embodiment, Figure 4 This is a schematic diagram of a signature verification process provided by an embodiment of the present invention. In this embodiment, the number of actual target signature images is n, that is, there are n authorized users performing handwritten signature operations at the scene of handling corporate business, and m baseline individual signature images of authorized users are reserved. Where m and n are both integers greater than or equal to 1, and m is greater than n. Figure 4 As shown, the signature verification process in this embodiment includes:

[0086] S410. Collect baseline individual signature images of m authorized users.

[0087] In this embodiment, signature images of m authorized users can be obtained by capturing signatures on a handwriting tablet or by scanning a document carrying a handwritten signature and extracting the signature area.

[0088] S420. Extract the baseline individual signature features from each baseline individual signature image.

[0089] In this embodiment, based on the pixel coordinate information of each benchmark individual signature image, the authentic mode function components are obtained using empirical mode decomposition and singular value decomposition. An initial matrix is ​​then created, and singular value decomposition is performed on the initial matrix to obtain the energy value feature vector.

[0090] S430. Merge the baseline individual signature features to obtain the baseline merged signature features, and store the baseline merged signature features.

[0091] In this embodiment, the initial matrix corresponding to the handwriting feature of the benchmark individual in each benchmark individual signature feature is superimposed with data, and the energy value feature vector corresponding to the strength feature of the benchmark individual in each benchmark individual signature feature is superimposed with data to obtain a new merged matrix and energy value feature vector, which are used as the corresponding benchmark merged signature feature, and the benchmark merged signature feature is stored in a database or a file.

[0092] S440: Collect the target actual signature images of n authorized users on site.

[0093] S450. Merge the actual individual signature features corresponding to the target actual signature image to obtain the actual merged signature features.

[0094] S460, Obtain signature verification rules.

[0095] S470. Determine the corresponding signature verification result based on the signature verification rules, the benchmark merged signature features, and the actual merged signature features.

[0096] Figure 5 This is a flowchart illustrating an automatic comparison of multiple signatures provided in an embodiment of the present invention. For example... Figure 5 As shown, an optimal signature path is found between the actual merged signature features of multiple people on-site and the baseline merged signature features of multiple people reserved. The distances of the optimal signature path from the on-site signature (i.e., the signature represented by the actual merged signature features) and the reserved signature (i.e., the signature represented by the baseline merged signature features) are calculated, which serve as the corresponding actual signature distance and baseline signature distance. Based on the pre-configured similarity mapping table, the number of successful signature matches is calculated; then, according to the signature verification rules for multiple people, it is determined whether the number of successful signature matches on-site meets the business processing requirements.

[0097] In one embodiment, Figure 6 This is a schematic diagram of the structure of a signature verification device provided in an embodiment of the present invention. Figure 6As shown, the device includes: a first acquisition module 610, a first merging module 620, a first determination module 630, and a second determination module 640.

[0098] The first acquisition module 610 is used to acquire the actual individual signature features of at least two actual signature images of the target object.

[0099] The first merging module 620 is used to merge the actual individual signature features using a preset merging strategy to obtain the actual merged signature features corresponding to the target object.

[0100] The first determining module 630 is used to determine the number of successful signature matches based on the comparison results of the benchmark merged signature features that match the actual merged signature features and the target object.

[0101] The second determining module 640 is used to determine the signature verification result of the target object based on the number of successful signature matches and pre-configured signature verification rules.

[0102] In one embodiment, the signature verification device further includes:

[0103] The second acquisition module is used to acquire at least two original actual signature images corresponding to the target object;

[0104] The processing module is used to normalize each original actual signature image to obtain the corresponding target actual signature image.

[0105] In one embodiment, the processing module includes:

[0106] The first acquisition unit is used to acquire the initial image size of each original actual signature image;

[0107] The processing unit is used to normalize each original actual signature image when the initial image size reaches the image size threshold, so as to obtain the target actual signature image of the target image size.

[0108] In one embodiment, the actual individual signature features include at least: actual individual handwriting features and actual individual pressure features.

[0109] In one embodiment, the first acquisition module 610 includes:

[0110] The second acquisition unit is used to acquire pixel coordinate information of at least two actual signature images of the target object;

[0111] The first determining unit is used to determine an initial matrix for characterizing individual handwriting features based on pixel coordinate information;

[0112] The decomposition unit is used to perform singular value decomposition on the initial matrix to obtain energy value eigenvectors that characterize individual strength features.

[0113] In one embodiment, the first merging module 620 includes:

[0114] The first merging unit is used to superimpose the initial matrix corresponding to the handwriting features of each actual individual to obtain the actual merged handwriting features corresponding to the target object.

[0115] The second merging unit is used to superimpose the energy value feature vectors corresponding to the actual individual force characteristics of each actual individual to obtain the actual merging force characteristics of the target object.

[0116] In one embodiment, the first determining module 630 includes:

[0117] The second determining unit is used to determine the optimal signature path between the actual merged signature feature and the benchmark merged signature feature using a preset path matching algorithm.

[0118] The third determining unit is used to determine the distance between the optimal signature path and the actual merged signature feature and the benchmark merged signature feature, which are used as the corresponding actual signature distance and benchmark signature distance.

[0119] The fourth determining unit is used to determine the number of successful signature matches based on the actual signature distance and the benchmark signature distance.

[0120] In one embodiment, the signature verification device further includes:

[0121] The third acquisition module is used to acquire a pre-configured similarity mapping table; wherein, the similarity mapping table is used to represent the mapping relationship between similarity and the number of successful signature matches;

[0122] Correspondingly, the fourth determining unit includes:

[0123] The first determining subunit is used to determine the actual similarity between the actual merged signature feature and the benchmark merged signature feature based on the actual signature distance and the benchmark signature distance;

[0124] The second determining subunit is used to determine the number of successful signature matches based on the actual similarity and the similarity mapping table.

[0125] In one embodiment, the second determining module 640 includes:

[0126] The fifth determining unit is used to determine the signature success matching threshold corresponding to the target object based on the signature verification rules;

[0127] The sixth determining unit is used to determine the signature verification result of the target object based on the comparison result between the number of successful signature matches and the successful signature match threshold.

[0128] In one embodiment, the signature verification device further includes:

[0129] The fourth acquisition module is used to acquire the baseline individual signature features of each baseline individual signature image corresponding to the target object;

[0130] The second merging module is used to merge the baseline individual signature features using a preset merging strategy to obtain the baseline merged signature features of the target object.

[0131] The encryption module is used to encrypt the baseline merged signature feature based on the encryption level of the target object;

[0132] The storage module is used to store the encrypted base signature features to the target storage path.

[0133] In one embodiment, the storage module is specifically used to store the baseline merged signature features corresponding to the target object and the pre-configured signature verification rules into one of the individual feature files in the target storage path, so as to obtain an object signature feature file that matches the target object.

[0134] The signature verification device provided in the embodiments of the present invention can execute the signature verification method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0135] In one embodiment, Figure 7 This is a structural block diagram of a signature verification electronic device provided in an embodiment of the present invention, such as... Figure 7 The diagram illustrates a schematic representation of an electronic device 10 that can be used to implement embodiments of the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0136] like Figure 7As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0137] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0138] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as signature verification methods.

[0139] In some embodiments, the signature verification method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or mounted on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the signature verification method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the signature verification method by any other suitable means (e.g., by means of firmware).

[0140] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0141] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0142] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0143] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0144] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0145] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0146] This invention also provides a computer program product, including a computer program that, when executed by a processor, implements the signature verification method provided in any embodiment of this application.

[0147] In implementing the computer program product, computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof. Programming languages ​​include object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0148] Note that the above description is merely a preferred embodiment of the present invention and the technical principles employed. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and various obvious changes, readjustments, and substitutions can be made without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the above embodiments, and may include many other equivalent embodiments without departing from the concept of the present invention, the scope of which is determined by the scope of the appended claims.

Claims

1. A signature verification method, characterized in that, include: Obtain the actual individual signature features of at least two actual signature images corresponding to the target object; The actual individual signature features are merged using a preset merging strategy to obtain the actual merged signature features corresponding to the target object; The number of successful signature matches is determined based on the comparison results between the actual merged signature features and the benchmark merged signature features that match the target object. The signature verification result of the target object is determined based on the number of successful signature matches and the pre-configured signature verification rules.

2. The method according to claim 1, characterized in that, The method further includes: Obtain at least two original actual signature images corresponding to the target object; Each of the original actual signature images is normalized to obtain the corresponding target actual signature image.

3. The method according to claim 2, characterized in that, The step of normalizing each of the original actual signature images to obtain the corresponding target actual signature image includes: Obtain the initial image size for each of the original actual signature images; When the initial image size reaches the image size threshold, each of the original actual signature images is normalized to obtain the target actual signature image of the target image size.

4. The method according to claim 1, characterized in that, The actual individual signature features include at least: actual individual handwriting features and actual individual pressure features.

5. The method according to claim 1, characterized in that, The acquisition of the actual individual signature features of at least two actual signature images corresponding to the target object includes: Obtain the pixel coordinate information of at least two actual signature images corresponding to the target object; An initial matrix for characterizing individual handwriting features is determined based on the pixel coordinate information; Singular value decomposition is performed on the initial matrix to obtain an energy value feature vector that characterizes the individual force characteristics.

6. The method according to claim 4, characterized in that, The step of merging the actual individual signature features using a preset merging strategy to obtain the actual merged signature features corresponding to the target object includes: The initial matrix corresponding to the handwriting features of each actual individual is superimposed to obtain the actual merged handwriting features corresponding to the target object. The energy value feature vectors corresponding to the actual individual force characteristics of each object are superimposed to obtain the actual combined force characteristics of the target object.

7. The method according to claim 1, characterized in that, The determination of the number of successful signature matches based on the comparison results between the actual merged signature features and the benchmark merged signature features that match the target object includes: The optimal signature path between the actual merged signature feature and the benchmark merged signature feature is determined using a preset path matching algorithm; Determine the distances between the optimal signature path and the actual merged signature feature and the benchmark merged signature feature, and use them as the corresponding actual signature distance and benchmark signature distance; The number of successful signature matches is determined based on the actual signature distance and the baseline signature distance.

8. The method according to claim 7, characterized in that, Also includes: Obtain a pre-configured similarity mapping table; wherein the similarity mapping table is used to represent the mapping relationship between the similarity and the number of successful signature matches; Accordingly, determining the number of successful signature matches based on the actual signature distance and the baseline signature distance includes: The actual similarity between the actual merged signature feature and the benchmark merged signature feature is determined based on the actual signature distance and the benchmark signature distance. The number of successful signature matches is determined based on the actual similarity and the similarity mapping table.

9. The method according to claim 1, characterized in that, The process of determining the signature verification result of the target object based on the number of successful signature matches and pre-configured signature verification rules includes: Based on the signature verification rules, determine the signature success matching threshold corresponding to the target object; The signature verification result of the target object is determined based on the comparison between the number of successful signature matches and the successful signature match threshold.

10. The method according to claim 1, characterized in that, The method further includes: Obtain the baseline individual signature features of each baseline individual signature image corresponding to the target object; The baseline individual signature features are merged using a preset merging strategy to obtain the baseline merged signature features of the target object; The baseline merged signature feature is encrypted based on the encryption level of the target object; The encrypted base signature is then stored in the target storage path.

11. The method according to claim 10, characterized in that, The step of storing each encrypted base signature feature in the target storage path includes: The baseline merged signature features corresponding to the target object, along with the pre-configured signature verification rules, are stored in one of the individual feature files in the target storage path to obtain an object signature feature file that matches the target object.

12. A signature verification device, characterized in that, include: The first acquisition module is used to acquire the actual individual signature features of at least two actual signature images corresponding to the target object; The first merging module is used to merge the actual individual signature features using a preset merging strategy to obtain the actual merged signature features corresponding to the target object. The first determining module is used to determine the number of successful signature matches based on the comparison result of the actual merged signature features and the benchmark merged signature features that match the target object. The second determining module is used to determine the signature verification result of the target object based on the number of successful signature matches and the pre-configured signature verification rules.

13. A signature verification electronic device, characterized in that, It includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the signature verification method as described in any one of claims 1-11.

14. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the signature verification method as described in any one of claims 1-11.

15. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the signature verification method as described in any one of claims 1-11.

Images