CN115953809A - Fingerprint verification method and device, storage medium and electronic device - Google Patents
Fingerprint verification method and device, storage medium and electronic device Download PDFInfo
- Publication number
- CN115953809A CN115953809A CN202211698846.8A CN202211698846A CN115953809A CN 115953809 A CN115953809 A CN 115953809A CN 202211698846 A CN202211698846 A CN 202211698846A CN 115953809 A CN115953809 A CN 115953809A
- Authority
- CN
- China
- Prior art keywords
- fingerprint
- feature
- similarity
- determining
- minutiae
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Collating Specific Patterns (AREA)
Abstract
The embodiment of the invention provides a fingerprint verification method, a fingerprint verification device, a storage medium and an electronic device, wherein the method comprises the following steps: extracting a first feature of a fingerprint to be verified; determining a first similarity between a first global feature of each first minutia included in the first features and a second global feature of each second minutia in second features of each fingerprint included in the fingerprint library, wherein the second features of each fingerprint are features obtained by feature fusion of features in a plurality of images of the fingerprint; determining a second similarity between the fingerprint to be verified and each fingerprint included in the fingerprint library based on the first similarity; and determining that the fingerprint to be verified is verified successfully under the condition that the similarity meeting the preset condition exists in the second similarities. By the method and the device, the problem of inaccurate fingerprint verification in the related technology is solved, and the effect of improving the fingerprint verification accuracy is achieved.
Description
Technical Field
The embodiment of the invention relates to the field of image identification, in particular to a fingerprint verification method, a fingerprint verification device, a fingerprint verification storage medium and an electronic device.
Background
With the development and progress of society, the actual need for rapid, effective and automatic personal identification is increasingly urgent. As an important issue of biometric identification technology, fingerprint identification technology is receiving more and more attention because of its high uniqueness and strong stability. Fingerprint identification technology is applied to the criminal investigation field at first, and in recent years, the technology is gradually popularized to people's daily life, such as attendance, entrance guard, safe deposit box, etc. Conventional fingerprint identification techniques typically include steps of fingerprint preprocessing, fingerprint minutiae extraction, fingerprint minutiae matching, and the like.
However, there is a problem in the related art that fingerprint authentication is inaccurate.
In view of the above problems in the related art, no effective solution has been proposed.
Disclosure of Invention
The embodiment of the invention provides a fingerprint verification method, a fingerprint verification device, a storage medium and an electronic device, which are used for at least solving the problem of inaccurate fingerprint verification in the related technology.
According to an embodiment of the present invention, there is provided a fingerprint authentication method including: extracting a first feature of a fingerprint to be verified; determining a first similarity between a first global feature of each first minutia included in the first features and a second global feature of each second minutia in second features of each fingerprint included in a fingerprint library, wherein the second feature of each fingerprint is a feature obtained by feature fusion of features in a plurality of images of the fingerprint; determining a second similarity between the fingerprint to be verified and each fingerprint included in the fingerprint library based on the first similarity; and determining that the fingerprint to be verified is verified successfully under the condition that the similarity meeting a preset condition exists in the second similarities.
According to another embodiment of the present invention, there is provided a fingerprint authentication apparatus including: the extraction module is used for extracting a first characteristic of the fingerprint to be verified; a first determining module, configured to determine a first similarity between a first global feature of each first minutia included in the first features and a second global feature of each second minutia in second features of each fingerprint included in a fingerprint library, where the second feature of each fingerprint is a feature obtained by feature fusion of features in multiple images of the fingerprint; a second determining module, configured to determine, based on the first similarity, a second similarity between the fingerprint to be verified and each fingerprint included in the fingerprint library; and the verification module is used for determining that the fingerprint to be verified is verified successfully under the condition that the similarity meeting the preset condition exists in the second similarity.
According to a further embodiment of the present invention, there is also provided a computer-readable storage medium having a computer program stored thereon, wherein the computer program is arranged to perform the steps of any of the above method embodiments when executed.
According to yet another embodiment of the present invention, there is also provided an electronic device, comprising a memory in which a computer program is stored and a processor configured to run the computer program to perform the steps of any of the method embodiments described above.
According to the fingerprint verification method and device, the first feature of the fingerprint to be verified is extracted, the first similarity between the first global feature of each first minutia included in the first feature and the second global feature of each second minutia included in the second feature of each fingerprint included in the fingerprint library is determined, the second similarity between the fingerprint to be verified and each fingerprint included in the fingerprint library is determined according to the first similarity, the second feature of each fingerprint is obtained by feature fusion of features in a plurality of images of the fingerprint, and the fingerprint to be verified is determined to be verified successfully under the condition that the similarity meeting the preset condition exists in the second similarity. The second features of each fingerprint in the fingerprint library are fused with the features of the corresponding image of the fingerprint, so that the randomness and the contingency of a single fingerprint image are reduced, and the accuracy of the determined first similarity is improved. Therefore, the problem of inaccurate fingerprint verification in the related technology can be solved, and the effect of improving the fingerprint verification accuracy is achieved.
Drawings
Fig. 1 is a block diagram of a hardware configuration of a mobile terminal according to a fingerprint authentication method of an embodiment of the present invention;
FIG. 2 is a flow chart of a method of authentication of a fingerprint according to an embodiment of the present invention;
FIG. 3 is a fingerprint preprocessing flow diagram according to an exemplary embodiment of the present invention;
FIG. 4 is a determination of a second similarity between a fingerprint to be authenticated and each of the fingerprints included in the fingerprint library according to an exemplary embodiment of the present invention;
FIG. 5 is a schematic diagram of feature fusion according to an exemplary embodiment of the present invention;
FIG. 6 is a flow diagram of a method for authenticating a fingerprint according to a specific embodiment of the present invention;
FIG. 7 is a feature verification flow diagram in accordance with a specific embodiment of the present invention;
fig. 8 is a block diagram of a fingerprint authentication apparatus according to an embodiment of the present invention.
Detailed Description
Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings in conjunction with the embodiments.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order.
The method embodiments provided in the embodiments of the present application may be executed in a mobile terminal, a computer terminal, or a similar computing device. Taking an example of the present invention running on a mobile terminal, fig. 1 is a block diagram of a hardware structure of the mobile terminal of a fingerprint authentication method according to an embodiment of the present invention. As shown in fig. 1, the mobile terminal may include one or more (only one shown in fig. 1) processors 102 (the processor 102 may include, but is not limited to, a processing device such as a microprocessor MCU or a programmable logic device FPGA), and a memory 104 for storing data, wherein the mobile terminal may further include a transmission device 106 for communication functions and an input-output device 108. It will be understood by those skilled in the art that the structure shown in fig. 1 is only an illustration, and does not limit the structure of the mobile terminal. For example, the mobile terminal may also include more or fewer components than shown in FIG. 1, or have a different configuration than shown in FIG. 1.
The memory 104 may be used to store computer programs, for example, software programs and modules of application software, such as a computer program corresponding to the fingerprint authentication method in the embodiment of the present invention, and the processor 102 executes various functional applications and data processing by running the computer programs stored in the memory 104, so as to implement the above-mentioned method. The memory 104 may include high speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include memory located remotely from the processor 102, which may be connected to the mobile terminal over a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The transmission device 106 is used for receiving or transmitting data via a network. Specific examples of the network described above may include a wireless network provided by a communication provider of the mobile terminal. In one example, the transmission device 106 includes a Network adapter (NIC), which can be connected to other Network devices through a base station so as to communicate with the internet. In one example, the transmission device 106 may be a Radio Frequency (RF) module, which is used to communicate with the internet in a wireless manner.
In the present embodiment, a method for verifying a fingerprint is provided, and fig. 2 is a flowchart of a method for verifying a fingerprint according to an embodiment of the present invention, as shown in fig. 2, the flowchart includes the following steps:
step S202, extracting a first characteristic of a fingerprint to be verified;
step S204, determining a first similarity between a first global feature of each first minutia included in the first features and a second global feature of each second minutia in second features of each fingerprint included in a fingerprint library, wherein the second features of each fingerprint are features obtained by feature fusion of features in a plurality of images of the fingerprint;
step S206, determining a second similarity between the fingerprint to be verified and each fingerprint included in the fingerprint database based on the first similarity;
step S208, under the condition that the similarity meeting the preset condition exists in the second similarity, determining that the fingerprint to be verified is verified successfully.
In the above embodiment, the fingerprint to be verified may be a fingerprint acquired by a target device, and the target device may include an intelligent terminal, a fingerprint acquisition instrument, and the like, such as a smart phone, a smart watch, a tablet computer, an intelligent lock, a safe and the like, which are integrated with a fingerprint acquisition function. The fingerprint repository may be a fingerprint repository stored in a storage unit of the target device, and may include one or more fingerprints and fingerprint features corresponding to each fingerprint. The fingerprints in the fingerprint repository may be fingerprints that have been previously registered with the target device. When fingerprint registration is carried out, the first fingerprint collected by the target equipment can be determined as the reference fingerprint, fingerprint collection is carried out again, and whether the currently collected fingerprint and the reference fingerprint are the same fingerprint or not is verified. For example, it may be determined whether the currently captured fingerprint and the reference fingerprint are the same fingerprint by determining the similarity of the captured fingerprint and the reference fingerprint. For example, when the similarity is greater than a predetermined threshold, the two fingerprints may be considered to belong to the same fingerprint. And when the two fingerprints are determined to belong to the same fingerprint, fusing the characteristics of the currently acquired fingerprint and the characteristics of the reference fingerprint, and determining the fused characteristics as the characteristics of the reference fingerprint. After the characteristic fusion is carried out, the fingerprints can be continuously collected, whether the collected fingerprints and the reference fingerprints are the same fingerprints or not is verified, and when the fingerprints are the same, the fingerprint characteristic fusion is carried out. When the number of fused fingerprints reaches a predetermined number, the finally obtained features may be determined as features of the reference fingerprint and stored in the fingerprint library.
In the above embodiment, the target device, such as a fingerprint acquisition instrument, may be pressed according to the acquisition requirement to acquire the fingerprint image, and after completing fingerprint acquisition, the acquired fingerprint image may be preprocessed. The fingerprint preprocessing can comprise the steps of segmentation, calculation of a direction field and a frequency field, enhancement, binarization, thinning and the like. The flow chart of fingerprint preprocessing can be seen in fig. 3. After fingerprint preprocessing is completed, feature extraction may be performed on the preprocessed fingerprint image. Fingerprint feature extraction generally refers to extracting fingerprint minutiae and recording minutiae information. That is, the first feature includes minutiae information of each minutia and global features of each minutia. The minutiae information may expressed as M = { M 1 ，m 2 ，...m k }，m i ＝{x i ，y i ，θ i K, where M represents a set of extracted minutiae points, M represents a single minutiae point, x represents a minutiae point abscissa, y represents a minutiae point ordinate, and θ represents a minutiae point direction. The global feature may be a feature determined from the minutiae information.
In the above embodiment, after the first feature of the fingerprint to be verified is extracted, feature comparison may be performed. I.e. determining a first similarity between the first global feature of each first minutia comprised in the first feature and the second global feature of each second minutia comprised in the second feature of each fingerprint of the fingerprint library, and determining a second similarity between the fingerprint to be authenticated and each fingerprint of the fingerprint library based on the first similarity. When the maximum similarity in the second similarities is greater than the preset similarity, it can be considered that the second similarities have the similarity meeting the preset condition, and it is determined that the fingerprint to be verified is verified successfully. After feature comparison, a similarity set S and a maximum similarity Stop1 between the fingerprint to be verified and all the fingerprints in the fingerprint database can be obtained, and then the maximum similarity is compared with a set similarity threshold. If the maximum similarity is larger than the threshold value, the verification is passed; otherwise, the verification fails. The verification method can
S＝{S 1 ，S 2 ，...S k }，S top1 ＝max(S)
Is shown as
The main body of the above steps may be a target device, a processor, etc., or a device integrated with a fingerprint acquisition device and a data processing device, but is not limited thereto.
According to the fingerprint verification method and device, the first feature of the fingerprint to be verified is extracted, the first similarity between the first global feature of each first minutia included in the first feature and the second global feature of each second minutia included in the second feature of each fingerprint included in the fingerprint library is determined, the second similarity between the fingerprint to be verified and each fingerprint included in the fingerprint library is determined according to the first similarity, the second feature of each fingerprint is obtained by feature fusion of features in a plurality of images of the fingerprint, and the fingerprint to be verified is determined to be successfully verified under the condition that the similarity meeting the preset condition exists in the second similarity. The second features of each fingerprint in the fingerprint library are fused with the features of the corresponding image of the fingerprint, so that the randomness and the contingency of a single fingerprint image are reduced, and the accuracy of the determined first similarity is improved. Therefore, the problem of inaccurate fingerprint verification in the related art can be solved, and the effect of improving the fingerprint verification accuracy is achieved.
In an exemplary embodiment, determining a first similarity between the first global feature of each first minutia comprised in the first feature and the second global feature of each second minutia of the second features of each fingerprint comprised in the fingerprint library comprises: performing the following operation for each first minutia included in the first feature to obtain a score associated with each first minutiaThe first global feature: determining a second minutia included in the first feature and closest to the first minutia, determining a first distance between the first minutia and the second minutia, determining a first angle between a first line between the first minutia and the second minutia and the direction of the first minutia, determining a second angle between the first line and the direction of the second minutia, and determining the first distance, the first angle and the second angle as the first global feature; performing the following operation on the first global feature of each first minutia to obtain the first similarity between the first global feature and each second global feature; determining a first arithmetic square root of a square of a difference of the first distance and a second distance comprised in the second global feature, determining a second arithmetic square root of a square of a difference of the first angle and a third angle comprised in the second global feature, determining a third arithmetic square root of a square of a difference of the second angle and a fourth angle comprised in the second global feature, determining the first similarity based on the first arithmetic square root, the second arithmetic square root and the third arithmetic square root. In this embodiment, for each first minutia in the first feature, a first global feature for each first minutia may be determined. When the first global feature is determined, a second minutia point closest to the first minutia point may be searched for in the first feature, and the first distance between the first minutia point and the second minutia point, the first angle, and the second angle are determined as the first global feature. For example, for minutiae m i Finding the detail point m nearest to it j Then the distance d, the included angle alpha and the included angle beta are taken as the minutiae point m i Global feature f of i ＝{d i ，α i ，β i }. After determining the global features, a first similarity of all minutiae pairs of the two fingerprints may be calculated based on the global features of the minutiae points. The first similarity may be based on a first arithmetic square root of a square of a difference between the first distance and a second distance included in the second global feature, the first angle, and the second global featureA second arithmetic square root of the square of the difference of the included third angles and a third arithmetic square root of the square of the difference of the second angles and fourth angles included in the second global feature. Wherein the first arithmetic square root can be expressed as
The second arithmetic square root can be expressed as->
Third Algorithm Square root can be expressed as ^ greater>
In one exemplary embodiment, determining the first degree of similarity based on the first square arithmetic root, the second square arithmetic root, and the third square arithmetic root comprises: determining a first sum of the first arithmetic square root, the second arithmetic square root, and the third arithmetic square root; determining the first sum as the first similarity. In the present embodiment, the first similarity may be represented as s (i, j) = d (i, j) + α (i, j) + β (i, j).
In an exemplary embodiment, determining a second similarity between the fingerprint to be authenticated and each fingerprint included in the fingerprint library based on the first similarity comprises: performing the following for each first fingerprint comprised in the fingerprint library to determine the second similarity of the fingerprint to be authenticated to the first fingerprint: matching the second minutiae and the first minutiae included in the first fingerprint based on the first similarity to obtain a plurality of first target minutiae pairs; determining a target number of the first target minutiae pairs; determining a third similarity included in the first similarity and corresponding to each first target minutiae pair; determining a second sum of the third similarities; determining a ratio of the second sum to the target number as the second similarity. In this embodiment, the matching results of the two fingerprint minutiae can be obtained and recorded by hungary matching according to the first similarity of the calculated minutiae pairs, and finally, the similarity of the two fingerprints is calculated according to the matching results. And determining a second minutia matched with the first minutia in the minutiae in each first fingerprint according to Hungarian matching, and determining the second minutia and the first minutia as a first target pair of minutiae. The similarity between the first minutiae and the second minutiae may be greater than the similarities of other first minutiae to minutiae included in the first fingerprint other than the second minutiae. Alternatively, the similarity between the first minutiae and the second minutiae may be greater than the similarities between other first minutiae and minutiae other than the second minutiae included in the first fingerprint, and the similarity is greater than a preset threshold.
In the above embodiment, after a plurality of first target minutiae pairs are determined, the target number of the first target minutiae pairs may be determined, the third similarity corresponding to each first target minutiae pair may be determined, and a ratio of a second sum of the plurality of third similarities to the target number may be determined as the second similarity. Wherein the second similarity can be expressed as
Wherein n and m respectively represent the number of two fingerprint minutiae, and p represents the minimum value of n and m, namely the target number. Wherein a flowchart for determining a second similarity between a fingerprint to be authenticated and each fingerprint comprised in the fingerprint library can be seen in fig. 4.
In an exemplary embodiment, after determining that the fingerprint to be verified is successfully verified, the method further comprises: determining a second fingerprint included in the fingerprint library corresponding to a maximum similarity included in the second similarities; matching the minutiae included in the second fingerprint with the first minutiae included in the fingerprint to be verified to obtain a second target minutiae pair; determining a fourth similarity included in the first similarity and corresponding to each second target minutiae pair; determining a fifth similarity included in the fourth similarity and a sixth similarity with the similarity being greater than or equal to a first predetermined threshold; determining a third target detail point pair corresponding to the fifth similarity and a fourth target detail point pair corresponding to the sixth similarity, which are included in the second target detail point pair; adding the features of the minutiae of the fingerprint to be verified included in the third target pair of minutiae to the second features of the second fingerprint; fusing the features corresponding to the detail points included in the fourth target detail point pair to obtain a first fused feature; updating a feature included in the second feature corresponding to the fourth target pair of minutiae to the first fused feature. In this embodiment, after the fingerprint to be verified is successfully verified, the fingerprint features to be verified and the features with the maximum similarity in the feature library may be fused. And replacing the fused features with the features of the corresponding original feature library. The feature fusion schematic diagram can refer to fig. 5, as shown in fig. 5, the dotted line represents a minutiae matching relationship, the numerical value represents a minutiae similarity, the minutiae similarity in the feature to be fused, which is less than a first predetermined threshold, is directly added to the reference feature, and the minutiae, which is greater than or equal to the first predetermined threshold, is fused with the corresponding minutiae in the reference feature. And completing feature fusion until all the minutiae points in the matching result are traversed, and obtaining a final fusion result.
In the embodiment, the feature updating strategy is used after the verification is passed, the feature template is updated in real time, the stability of the feature template is enhanced, the recognition rate is improved, and the false recognition rate is reduced.
In an exemplary embodiment, fusing features corresponding to the minutiae points included in the fourth target minutiae pair to obtain a first fused feature includes: determining a third characteristic of the first sub-minutiae and a fourth characteristic of the second sub-minutiae comprised in the fourth target pair of minutiae; determining a first average of a first abscissa included in the third feature and a second abscissa included in the fourth feature; determining a second average of a first ordinate included in the third feature and a second ordinate included in the fourth feature; determining a first direction angle and the fourth feature included in the third featureCharacterizing a third mean value of the included second direction angles; determining a feature including the first average value, the second average value, and the third average value as the first fusion feature. In this embodiment, the feature fusion may be fusion of minutiae information of minutiae, that is, the third feature and the fourth feature may be minutiae information. The third feature may be expressed as m i ＝(x i ,y i ,θ i ) The fourth feature can be expressed as m j ＝(x j ,y j ,θ j ). The first fused feature may be represented as
In an exemplary embodiment, before determining the first similarity between the first global feature of each first minutia included in the first features and the second global feature of each second minutia in the second features of each fingerprint included in the fingerprint library, the method further comprises: acquiring the fingerprint characteristics to be registered of the fingerprint to be registered; determining a seventh similarity between the fingerprint to be registered and a reference fingerprint based on the fingerprint features to be registered, wherein the reference fingerprint is a fingerprint acquired for the first time in a registration process; under the condition that the seventh similarity is larger than a third preset threshold value, fusing the fingerprint features to be registered with the reference fingerprint features of the reference fingerprint to obtain second fused features; updating the second fused feature to the reference fingerprint feature; registering the reference fingerprint and the reference fingerprint features in the fingerprint repository. In this embodiment, before fingerprint verification, fingerprint registration may also be performed first. Firstly, fingerprint collection is carried out, whether the collected fingerprint is the first fingerprint is determined, when the collected fingerprint is the first fingerprint, the fingerprint is determined as the reference fingerprint, and the characteristic of the fingerprint is determined as the characteristic of the reference fingerprint. And when the acquired fingerprint is not the first fingerprint, determining the fingerprint as the fingerprint to be registered, and determining the seventh similarity between the characteristics of the fingerprint to be registered and the characteristics of the reference fingerprint, namely if the extracted characteristics are the characteristics of the first fingerprint, taking the characteristics as the reference characteristics and directly checking to pass, otherwise, taking the characteristics as the characteristics to be checked and comparing the characteristics with the reference characteristics, comparing the similarity obtained by comparing the characteristics with a set threshold value, if the similarity is greater than the threshold value, checking to pass, otherwise, not checking to pass until the number of the characteristics passing the checking reaches the number of the characteristics required by the characteristic fusion. And then sequentially fusing the fingerprint features to be registered with the reference fingerprint features, determining the fused features as the reference fingerprint features, and registering the reference fingerprint features in a fingerprint database.
The following describes a fingerprint verification method with reference to specific embodiments:
fig. 6 is a flowchart of a fingerprint verification method according to an embodiment of the present invention, and as shown in fig. 6, the flowchart includes an enrollment phase and a verification phase, including:
1. registration phase
1.1 fingerprint Collection
And pressing the fingerprint acquisition instrument according to the acquisition requirement to acquire a fingerprint image.
1.2 pretreatment
After completing fingerprint acquisition, the acquired fingerprint image needs to be preprocessed. The fingerprint preprocessing generally comprises the steps of segmentation, calculation of a direction field and a frequency field, enhancement, binarization, thinning and the like.
1.3 feature extraction
After finishing the fingerprint preprocessing, feature extraction needs to be performed on the preprocessed fingerprint image. Fingerprint feature extraction generally refers to extracting fingerprint minutiae and recording minutia information:
M＝{m 1 ，m 2 ，...m k }，m i ＝{x i ，y i ，θ i }，i＝1，2，...k，
where M represents the extracted minutiae set, M represents a single minutia, x represents the minutiae abscissa, y represents the minutiae ordinate, and θ represents the minutiae direction.
1.4 feature verification
Referring to fig. 7, as shown in fig. 7, if the extracted feature is the feature of the first fingerprint, the feature is used as the reference feature and is directly verified, otherwise, the feature is used as the feature to be verified and is compared with the reference feature by the feature comparison 1. And then comparing the similarity obtained by the feature comparison with a set threshold, if the similarity is greater than the threshold, the verification is passed, otherwise, the verification is not passed until the number of the features passing the verification reaches the number of the features required by the feature fusion.
1.4.1 feature alignment
Wherein, the feature comparison flowchart can be seen in fig. 4, first, the detail point global feature construction is performed on two features respectively (for the detail point m) i Finding the detail point m nearest to it j Then, the distance d, the included angle alpha and the included angle beta are taken as the global characteristic f of the minutiae mi i )：
f i ＝{d i ，α i ，β i }
Then, calculating the similarity of all minutiae pairs of the two fingerprints based on the minutiae global features:
s(i，j)＝d(i，j)+α(i，j)+β(i，j)
and then according to the similarity of the minutiae pairs obtained by calculation, acquiring and recording the matching result of the two fingerprint minutiae by Hungary matching, and finally calculating the similarity of the two fingerprints according to the matching result:
1.5 feature fusion
According to the matching result of two fingerprint minutiae recorded by feature comparison (wherein a dotted line represents the matching relationship of the minutiae, and a numerical value represents the similarity of the minutiae), the minutiae with the similarity smaller than a threshold (0.6) in the feature to be fused are directly added into the reference feature, and the minutiae with the similarity larger than the threshold are fused with the corresponding minutiae in the reference feature), wherein the fusion mode is as follows:
m i ＝{x i ，y i ，θ i }，m j ＝{x j ，y j ，θ j }
and completing feature fusion until all the minutiae pairs in the matching result are traversed, and obtaining a final fusion result.
2. Verification phase
2.1 fingerprint Collection
The procedure is as in step 1.1.
2.2 pretreatment
The procedure is as in step 1.2.
2.3 feature extraction
This step is the same as step 1.3.
2.4 feature alignment
And comparing the verification fingerprint features with all fingerprint features in the feature library. The specific process of feature alignment is the same as step 1.4.1.
2.5 decision
After feature comparison, a similarity set S and a maximum similarity Stop1 between the verification fingerprint and all fingerprints in the feature library can be obtained, and then the maximum similarity is compared with a set similarity threshold. If the maximum similarity is larger than the threshold value, the verification is passed; otherwise, the verification fails.
2.6 feature fusion
And after the fingerprint verification is passed, fusing the verified fingerprint features with the maximum similarity in the feature library. The specific process of feature fusion is the same as step 1.5.
2.7 feature update
And replacing the fused features with the features of the corresponding original feature library.
In the embodiment, the multi-fingerprint fusion registration scheme is adopted, so that the randomness and the contingency in the registration stage are reduced, the recognition rate is improved, and the false recognition rate is reduced. A check mechanism is introduced into the multi-fingerprint fusion registration scheme, and a fusion method which does not depend on minutiae alignment is adopted, so that the accuracy of a fusion template is enhanced, the recognition rate is improved, and the false recognition rate is reduced. After the verification is passed, a feature updating strategy is used for updating the feature template in real time, so that the stability of the feature template is enhanced, the recognition rate is improved, and the false recognition rate is reduced.
Through the above description of the embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but the former is a better implementation mode in many cases. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which is stored in a storage medium (e.g., ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal device (e.g., a mobile phone, a computer, a server, or a network device) to execute the method according to the embodiments of the present invention.
In this embodiment, a fingerprint verification apparatus is further provided, and the apparatus is used to implement the foregoing embodiments and preferred embodiments, and the description of which has been already made is omitted. As used below, the term "module" may be a combination of software and/or hardware that implements a predetermined function. Although the means described in the embodiments below are preferably implemented in software, an implementation in hardware, or a combination of software and hardware is also possible and contemplated.
Fig. 8 is a block diagram showing the configuration of an apparatus for authenticating a fingerprint according to an embodiment of the present invention, as shown in fig. 8, the apparatus including:
an extraction module 82, configured to extract a first feature of a fingerprint to be verified;
a first determining module 84, configured to determine a first similarity between a first global feature of each first minutia included in the first features and a second global feature of each second minutia in second features of each fingerprint included in a fingerprint library, where the second feature of each fingerprint is a feature obtained by feature fusion of features in multiple images of the fingerprint;
a second determining module 86, configured to determine a second similarity between the fingerprint to be verified and each fingerprint included in the fingerprint library based on the first similarity;
and the verification module 88 is configured to determine that the fingerprint to be verified is verified successfully if the similarity meeting the predetermined condition exists in the second similarities.
In an exemplary embodiment, the first determining module 84 may determine the first similarity between the first global feature of each first minutia comprised in the first feature and the second global feature of each second minutia of the second features of each fingerprint comprised in the fingerprint library by: for each first minutia included in the first feature, performing the following operations, resulting in the first global feature associated with each first minutia: determining a second minutia point included in the first feature and closest to the first minutia point, determining a first distance between the first minutia point and the second minutia point, determining a first included angle between a first connecting line between the first minutia point and the second minutia point and the direction of the first minutia point, determining a second included angle between the first connecting line and the direction of the second minutia point, and determining the first distance, the first included angle and the second included angle as the first global feature; performing the following operation on the first global feature of each first minutia to obtain the first similarity between the first global feature and each second global feature; determining a first arithmetic square root of a square of a difference of the first distance and a second distance comprised in the second global feature, determining a second arithmetic square root of a square of a difference of the first angle and a third angle comprised in the second global feature, determining a third arithmetic square root of a square of a difference of the second angle and a fourth angle comprised in the second global feature, determining the first similarity based on the first arithmetic square root, the second arithmetic square root and the third arithmetic square root.
In an exemplary embodiment, the first determination module 84 may determine the first similarity based on the first arithmetic square root, the second arithmetic square root, and the third arithmetic square root by: determining a first sum of the first arithmetic square root, the second arithmetic square root, and the third arithmetic square root; determining the first sum as the first similarity.
In an exemplary embodiment, the second determining module 86 may determine the second similarity between the fingerprint to be verified and each fingerprint included in the fingerprint library based on the first similarity by: performing the following for each first fingerprint comprised in the fingerprint library to determine the second similarity of the fingerprint to be authenticated to the first fingerprint: matching the second minutiae and the first minutiae included in the first fingerprint based on the first similarity to obtain a plurality of first target minutiae pairs; determining a target number of the first target minutiae pairs; determining a third similarity included in the first similarity and corresponding to each first target minutiae pair; determining a second sum of the third similarities; determining a ratio of the second sum to the target number as the second similarity.
In an exemplary embodiment, the apparatus may be configured to, after determining that the fingerprint to be verified is successfully verified, determine a second fingerprint included in the fingerprint library that corresponds to a maximum similarity included in the second similarities; matching the minutiae included in the second fingerprint with the first minutiae included in the fingerprint to be verified to obtain a second target minutiae pair; determining a fourth similarity included in the first similarity and corresponding to each second target minutiae pair; determining a fifth similarity included in the fourth similarity and a sixth similarity with the similarity being greater than or equal to a first predetermined threshold; determining a third target minutiae pair corresponding to the fifth similarity and a fourth target minutiae pair corresponding to the sixth similarity, which are included in the second target minutiae pair; adding the features of minutiae of the fingerprint to be verified included in the third target pair of minutiae to the second features of the second fingerprint; fusing the features corresponding to the detail points included in the fourth target detail point pair to obtain a first fused feature; updating a feature included in the second feature corresponding to the fourth target pair of minutiae to the first fused feature.
In an exemplary embodiment, the apparatus may perform fusing the features corresponding to the minutiae included in the fourth target pair of minutiae to obtain a first fused feature by: determining a third characteristic of the first sub-minutiae and a fourth characteristic of the second sub-minutiae comprised in the fourth target pair of minutiae; determining a first average of a first abscissa included in the third feature and a second abscissa included in the fourth feature; determining a second average of a first ordinate included in the third feature and a second ordinate included in the fourth feature; determining a third average of a first direction angle included in the third feature and a second direction angle included in the fourth feature; determining a feature including the first average value, the second average value, and the third average value as the first fusion feature.
In an exemplary embodiment, the apparatus may be further configured to, before determining a first similarity between the first global feature of each first minutia included in the first features and the second global feature of each second minutia of the second features of each fingerprint included in the fingerprint library, obtain a fingerprint feature to be registered of the fingerprint to be registered; determining a seventh similarity between the fingerprint to be registered and a reference fingerprint based on the fingerprint features to be registered, wherein the reference fingerprint is a fingerprint acquired for the first time in a registration process; under the condition that the seventh similarity is larger than a third preset threshold value, fusing the fingerprint features to be registered with the reference fingerprint features of the reference fingerprint to obtain second fused features; updating the second fused feature to the reference fingerprint feature; registering the reference fingerprint and the reference fingerprint features in the fingerprint repository.
It should be noted that, the above modules may be implemented by software or hardware, and for the latter, the following may be implemented, but not limited to: the modules are all positioned in the same processor; alternatively, the modules are respectively located in different processors in any combination.
Embodiments of the present invention also provide a computer-readable storage medium having a computer program stored thereon, wherein the computer program is arranged to perform the steps of any of the above-mentioned method embodiments when executed.
In an exemplary embodiment, the computer-readable storage medium may include, but is not limited to: various media capable of storing computer programs, such as a usb disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic disk, or an optical disk.
Embodiments of the present invention also provide an electronic device comprising a memory having a computer program stored therein and a processor arranged to run the computer program to perform the steps of any of the above method embodiments.
In an exemplary embodiment, the electronic apparatus may further include a transmission device and an input/output device, wherein the transmission device is connected to the processor, and the input/output device is connected to the processor.
For specific examples in this embodiment, reference may be made to the examples described in the above embodiments and exemplary embodiments, and details of this embodiment are not repeated herein.
It will be apparent to those skilled in the art that the various modules or steps of the invention described above may be implemented using a general purpose computing device, they may be centralized on a single computing device or distributed across a network of computing devices, and they may be implemented using program code executable by the computing devices, such that they may be stored in a memory device and executed by the computing device, and in some cases, the steps shown or described may be performed in an order different than that described herein, or they may be separately fabricated into various integrated circuit modules, or multiple ones of them may be fabricated into a single integrated circuit module. Thus, the present invention is not limited to any specific combination of hardware and software.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A method of authenticating a fingerprint, comprising:
extracting a first feature of a fingerprint to be verified;
determining a first similarity between a first global feature of each first minutia included in the first features and a second global feature of each second minutia in second features of each fingerprint included in a fingerprint library, wherein the second feature of each fingerprint is a feature obtained by feature fusion of features in a plurality of images of the fingerprint;
determining a second similarity between the fingerprint to be verified and each fingerprint included in the fingerprint library based on the first similarity;
and determining that the fingerprint to be verified is verified successfully under the condition that the similarity meeting a preset condition exists in the second similarities.
2. A method according to claim 1, wherein determining a first similarity between the first global feature of each first minutia included in the first features and the second global feature of each second minutia in the second features of each fingerprint included in the library of fingerprints comprises:
for each first minutia included in the first feature, performing the following operations, resulting in the first global feature associated with each first minutia: determining a second minutia point included in the first feature and closest to the first minutia point, determining a first distance between the first minutia point and the second minutia point, determining a first included angle between a first connecting line between the first minutia point and the second minutia point and the direction of the first minutia point, determining a second included angle between the first connecting line and the direction of the second minutia point, and determining the first distance, the first included angle and the second included angle as the first global feature;
performing the following operation on the first global feature of each first minutia to obtain the first similarity between the first global feature and each second global feature; determining a first arithmetic square root of a square of a difference of the first distance and a second distance comprised in the second global feature, determining a second arithmetic square root of a square of a difference of the first angle and a third angle comprised in the second global feature, determining a third arithmetic square root of a square of a difference of the second angle and a fourth angle comprised in the second global feature, determining the first similarity based on the first arithmetic square root, the second arithmetic square root and the third arithmetic square root.
3. The method of claim 2, wherein determining the first similarity based on the first arithmetic square root, the second arithmetic square root, and the third arithmetic square root comprises:
determining a first sum of the first arithmetic square root, the second arithmetic square root, and the third arithmetic square root;
determining the first sum as the first similarity.
4. The method of claim 1, wherein determining a second similarity between the fingerprint to be authenticated and each fingerprint included in the fingerprint library based on the first similarity comprises:
for each first fingerprint included in the fingerprint library, performing the following operations to determine the second similarity of the fingerprint to be verified to the first fingerprint:
matching the second minutiae and the first minutiae included in the first fingerprint based on the first similarity to obtain a plurality of first target minutiae pairs;
determining a target number of the first target minutiae pairs;
determining a third similarity included in the first similarity and corresponding to each first target minutiae pair;
determining a second sum of the third similarities;
determining a ratio of the second sum to the target number as the second similarity.
5. The method of claim 1, wherein after determining that the fingerprint to be verified is successfully verified, the method further comprises:
determining a second fingerprint included in the fingerprint library corresponding to a maximum similarity included in the second similarities;
matching the minutiae included in the second fingerprint with the first minutiae included in the fingerprint to be verified to obtain a second target minutiae pair;
determining a fourth similarity included in the first similarity and corresponding to each second target minutiae pair;
determining a fifth similarity of which the similarity included in the fourth similarity is smaller than a first predetermined threshold and a sixth similarity of which the similarity is greater than or equal to the first predetermined threshold;
determining a third target minutiae pair corresponding to the fifth similarity and a fourth target minutiae pair corresponding to the sixth similarity, which are included in the second target minutiae pair;
adding the features of the minutiae of the fingerprint to be verified included in the third target pair of minutiae to the second features of the second fingerprint;
fusing the features corresponding to the minutiae included in the fourth target minutiae pair to obtain a first fused feature;
updating a feature included in the second feature corresponding to the fourth target pair of minutiae to the first fused feature.
6. The method according to claim 5, wherein fusing features corresponding to minutiae included in the fourth target pair of minutiae to obtain a first fused feature comprises:
determining a third characteristic of the first sub-minutiae and a fourth characteristic of the second sub-minutiae comprised in the fourth target pair of minutiae;
determining a first average of a first abscissa included in the third feature and a second abscissa included in the fourth feature;
determining a second average of a first ordinate included in the third feature and a second ordinate included in the fourth feature;
determining a third average of a first direction angle included in the third feature and a second direction angle included in the fourth feature;
determining a feature including the first average value, the second average value, and the third average value as the first fused feature.
7. A method according to claim 1, wherein prior to determining a first similarity between the first global feature of each first minutia comprised in the first features and the second global feature of each second minutia of the second features of each fingerprint comprised in the fingerprint library, the method further comprises:
acquiring the fingerprint characteristics to be registered of the fingerprint to be registered;
determining a seventh similarity between the fingerprint to be registered and a reference fingerprint based on the fingerprint features to be registered, wherein the reference fingerprint is a fingerprint acquired for the first time in a registration process;
under the condition that the seventh similarity is larger than a third preset threshold value, fusing the fingerprint features to be registered with the reference fingerprint features of the reference fingerprint to obtain second fused features;
updating the second fused feature to the reference fingerprint feature;
registering the reference fingerprint and the reference fingerprint features in the fingerprint repository.
8. An apparatus for verifying a fingerprint, comprising:
the extraction module is used for extracting a first feature of the fingerprint to be verified;
a first determining module, configured to determine a first similarity between a first global feature of each first minutia included in the first features and a second global feature of each second minutia in a second feature of each fingerprint included in a fingerprint library, where the second feature of each fingerprint is a feature obtained by feature fusion of features in multiple images of the fingerprint;
a second determining module, configured to determine, based on the first similarity, a second similarity between the fingerprint to be verified and each fingerprint included in the fingerprint library;
and the verification module is used for determining that the fingerprint to be verified is verified successfully under the condition that the similarity meeting the preset condition exists in the second similarity.
9. A computer-readable storage medium, in which a computer program is stored, wherein the computer program is arranged to perform the method of any of claims 1 to 7 when executed.
10. An electronic device comprising a memory and a processor, wherein the memory has stored therein a computer program, and wherein the processor is arranged to execute the computer program to perform the method of any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211698846.8A CN115953809A (en) | 2022-12-28 | 2022-12-28 | Fingerprint verification method and device, storage medium and electronic device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211698846.8A CN115953809A (en) | 2022-12-28 | 2022-12-28 | Fingerprint verification method and device, storage medium and electronic device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115953809A true CN115953809A (en) | 2023-04-11 |
Family
ID=87288761
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211698846.8A Pending CN115953809A (en) | 2022-12-28 | 2022-12-28 | Fingerprint verification method and device, storage medium and electronic device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115953809A (en) |
-
2022
- 2022-12-28 CN CN202211698846.8A patent/CN115953809A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US7151846B1 (en) | Apparatus and method for matching fingerprint | |
| CN102646190B (en) | A kind of authentication method based on biological characteristic, apparatus and system | |
| CN100414558C (en) | Automatic fingerprint distinguishing system and method based on template learning | |
| US20040042645A1 (en) | Fingerprint recognition method, and fingerprint control method and system | |
| Hemalatha | A systematic review on Fingerprint based Biometric Authentication System | |
| US20060117188A1 (en) | Biometric print quality assurance | |
| JP5710748B2 (en) | Biometric authentication system | |
| US20090169072A1 (en) | Method and system for comparing prints using a reconstructed direction image | |
| EP1825374B1 (en) | Biometric print quality assurance | |
| CN113221086B (en) | Offline face authentication method and device, electronic equipment and storage medium | |
| US10216786B2 (en) | Automatic identity enrolment | |
| WO2010069166A1 (en) | Fast fingerprint searching method and fast fingerprint searching system | |
| Rahman et al. | Automated student attendance system using fingerprint recognition | |
| Krish et al. | Pre‐registration of latent fingerprints based on orientation field | |
| CN111488798B (en) | Fingerprint identification method, fingerprint identification device, electronic equipment and storage medium | |
| Yuan et al. | A real time fingerprint recognition system based on novel fingerprint matching strategy | |
| Bistarelli et al. | An asymmetric fingerprint matching algorithm for Java Card TM | |
| CN113705366A (en) | Personnel management system identity identification method and device and terminal equipment | |
| CN115953809A (en) | Fingerprint verification method and device, storage medium and electronic device | |
| CN115527241A (en) | Fingerprint template updating method and device, embedded equipment and storage medium | |
| Al Taee et al. | A new approach for fingerprint authentication in biometric systems using BRISK algorithm | |
| CN113569839A (en) | Certificate identification method, system, device and medium | |
| Bistarelli et al. | An asymmetric fingerprint matching algorithm for java card TM | |
| Sharma et al. | Fingerprint matching Using Minutiae Extraction Techniques | |
| Gowandy et al. | ELECTRONIC VOTING SYSTEM BASED ON FINGERPRINT RECOGNITION AND RADIO FREQUENCY IDENTIFICATION |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |