TW201828136A - Fingerprint verification method and electronic device - Google Patents

Abstract

A fingerprint verification method and an electronic device are provided. The fingerprint verification method includes: obtaining a plurality of fingerprint images; comparing each of the plurality of fingerprint images with a preset fingerprint image to obtain a plurality of first comparing results; comparing each two of the plurality of fingerprint images with each other to obtain at least one second comparing result; and determining whether the plurality of fingerprint images are authenticated according to the plurality of first comparing results and the at least one second comparing result.

Description

Fingerprint verification method and electronic device

The present invention relates to a verification method, and in particular to a fingerprint verification method and an electronic device.

The types of biometrics include face, sound, iris, retina, vein, fingerprint, and palmprint recognition. Since each person's fingerprints are unique and fingerprints are not easily changed with age or physical health, fingerprint recognition technology has been widely used in various fields.

In general, according to different needs, the Fault Acceptance Rate (FAR) and the Fault Rejection Rate (FRR) are often used as evaluation indicators of the fingerprint identification system in the technical field of fingerprint identification. The error acceptance rate is a probability that a user who is illegal is mistakenly judged to be a legitimate user, and the lower the error acceptance rate, the higher the security of the fingerprint recognition device. The false rejection rate is a probability that a legitimate user is mistakenly judged to be an illegal user, and the lower the false rejection rate, the easier it is to use. For the time being, when fingerprint verification is to be performed, the fingerprint identification device captures a fingerprint image through a single press of the user for comparison. However, based on the influence of various factors, the verification by only one fingerprint image is likely to cause a fingerprint identification error, so that a legitimate user cannot pass the fingerprint verification, thereby affecting the security or convenience of the fingerprint identification device. Therefore, how to improve the accuracy of fingerprint verification is an important issue at present.

The invention provides a verification method, in particular a fingerprint verification method and an electronic device to which the fingerprint verification method is applied.

The fingerprint verification method of the present invention includes: acquiring a plurality of fingerprint images; comparing each of the plurality of fingerprint images with a preset fingerprint image to obtain a plurality of first comparison results; Each of the two fingerprint images in the fingerprint image is compared with each other to obtain at least one second comparison result; and determining the plurality of fingerprint images according to the plurality of first comparison results and the at least one second comparison result Whether it passed the verification.

In an embodiment of the invention, the fingerprint verification method further includes generating a plurality of initial scores according to the plurality of first alignment results. The step of determining whether the plurality of fingerprint images pass the verification according to the plurality of first comparison results and the at least one second comparison result comprises: adjusting the plurality according to the at least one second comparison result An initial score to obtain a plurality of verification scores; and determining whether the plurality of fingerprint images pass the verification according to the plurality of verification scores.

In an embodiment of the present invention, the step of determining whether the plurality of fingerprint images passes the verification according to the plurality of verification scores comprises determining whether the plurality of verification scores includes at least one first verification that meets a verification threshold value. fraction. If it is determined that the plurality of verification scores include the at least one first verification score, determining that the first fingerprint image in the plurality of fingerprint images corresponding to the at least one first verification score passes verification.

In an embodiment of the present invention, the fingerprint verification method further includes generating at least one reference comparison result according to the plurality of first comparison results, and according to the at least one reference comparison result and the at least one The second comparison result obtains at least one similarity parameter. The step of adjusting the plurality of initial scores according to the at least one second alignment result to obtain the plurality of verification scores includes adjusting the plurality of initial scores according to the at least one similarity parameter to obtain the plurality of Verification scores.

In an embodiment of the invention, the step of adjusting the plurality of initial scores according to the at least one similarity parameter to obtain the plurality of verification scores comprises determining whether the at least one similarity parameter is less than a similarity threshold value. If it is determined that the at least one similarity parameter is not less than the similarity threshold, the plurality of initial scores are adjusted according to the first rule to obtain the plurality of verification scores. If it is determined that the at least one similarity parameter is less than the similarity threshold, the plurality of initial scores are adjusted according to a second rule to obtain the plurality of verification scores.

The electronic device of the present invention comprises: an image capturing module, a comparison module and a verification module. The image capture module is used to acquire multiple fingerprint images. The comparison module is configured to compare each of the plurality of fingerprint images with a preset fingerprint image to obtain a plurality of first alignment results, and each of the plurality of fingerprint images The fingerprint images are compared to each other to obtain at least one second alignment result. The verification module is configured to determine, according to the plurality of first comparison results and the at least one second comparison result, whether the plurality of fingerprint images pass the verification.

In an embodiment of the invention, the comparison module is further configured to generate a plurality of initial scores according to the plurality of first alignment results. The verification module is configured to adjust the plurality of initial scores according to the at least one second comparison result to obtain a plurality of verification scores, and determine whether the plurality of fingerprint images pass the verification according to the plurality of verification scores.

In an embodiment of the invention, the verification module is configured to determine whether the plurality of verification scores includes at least one first verification score that meets a verification threshold. If the plurality of verification scores are determined to include the at least one first verification score, the verification module is configured to determine that the first fingerprint image of the plurality of fingerprint images corresponding to the at least one first verification score passes verification.

In an embodiment of the present invention, the comparison module is configured to generate at least one reference comparison result according to the plurality of first alignment results, and according to the at least one reference comparison result and the at least one The second alignment result obtains at least one similarity parameter. The verification module above adjusts the plurality of initial scores according to the at least one similarity parameter to obtain the plurality of verification scores.

In an embodiment of the invention, the verification module is configured to determine whether the at least one similarity parameter is less than a similarity threshold. If it is determined that the at least one similarity parameter is not less than the similarity threshold, the verification module is configured to adjust the plurality of initial scores according to the first rule to obtain the plurality of verification scores. If it is determined that the at least one similarity parameter is smaller than the similarity threshold, the verification module is configured to adjust the plurality of initial scores according to the second rule to obtain the plurality of verification scores.

Based on the above, the fingerprint verification method and the electronic device of the present invention can perform fingerprint verification by acquiring a plurality of fingerprint images and comparing the obtained plurality of fingerprint images one by one with a preset fingerprint image.

The above described features and advantages of the invention will be apparent from the following description.

The invention determines whether the fingerprint to be verified passes the verification by obtaining a plurality of fingerprint images of the fingerprint to be verified. And performing fingerprinting together by using a plurality of comparison results between each captured fingerprint image and a preset fingerprint image, and a plurality of comparison results between each of the captured two fingerprint images Verification improves the accuracy of fingerprint verification.

FIG. 1 is a block diagram of an electronic device according to an embodiment of the invention.

Referring to FIG. 1, the electronic device 10 of the embodiment is, for example, a smart phone, a tablet computer, a desktop computer or a notebook computer or other similar electronic device having a fingerprint sensor. The electronic device 10 includes a fingerprint sensor 110, a processor 120, and a storage device 130.

The fingerprint sensor 110 can be an optical, resistive, capacitive or other kind of sensing element for sensing a user's operation (eg, touching or approaching) to capture a fingerprint image. However, the invention is not limited thereto. Those skilled in the art can select the fingerprint sensor 110 that captures the fingerprint image in different ways according to actual needs.

The storage device 130 can be any type of fixed or removable random access memory (RAM), read-only memory (ROM), flash memory or Similar elements or combinations of the above elements. In the embodiment, the storage device 130 is configured to record the image capturing module 131, the comparison module 132, and the verification module 133. The modules are, for example, programs stored in the storage device 130. In another embodiment, the storage device 130 can be used to store fingerprint images captured by the fingerprint sensor 110.

The processor 120 is, for example, a central processing unit (CPU) or other programmable general purpose or special purpose microprocessor (Microprocessor), digital signal processor (DSP), programmable controller , Application Specific Integrated Circuits (ASICs), Programmable Logic Devices (PLDs), or other similar devices or a combination of these devices.

The processor 120 is coupled to the fingerprint sensor 110 and the storage device 130, and loads the image capturing module 131, the comparison module 132, and the verification module 133 from the storage device 130, thereby executing the present invention. Fingerprint verification method. The following is an example to illustrate this method.

2 is a flow chart of a fingerprint verification method according to an embodiment of the invention.

Referring to FIG. 2, the method of the present embodiment is applied to the electronic device 10 of FIG. 1, and the detailed steps of the fingerprint verification method of the present invention are described below with the components in the electronic device 10.

When the user wants to perform the fingerprint verification operation using the electronic device 10, first, in step S201, the processor 120 executes the image capturing module 131 to obtain a plurality of fingerprint images by the fingerprint sensor 110. In an embodiment, the electronic device 10 of FIG. 1 may further include a display device (not shown). The electronic device 10 can display a prompt message on the display device regarding the number of presses of the user input fingerprint, and the fingerprint sensor 110 captures a plurality of fingerprint images with each pressing action of the user. In an embodiment, the processor 120 can execute the image capturing module 131 and perform an image processing operation on the image captured by the fingerprint sensor 110 to obtain a fingerprint image to be used for comparison. The image processing operations described above may include performing grayscale processing on the fingerprint image, or analyzing features of the fingerprint image to calculate a geometric relation of the corresponding fingerprint image. The above geometric relationship may be, for example, characteristic information about the relative position of the fingerprint feature, the relative direction, or the distance between the features.

Next, in step S203, the processor 120 executes the comparison module 132 to compare the plurality of fingerprint images with the preset fingerprint image to obtain a plurality of first comparison results. The comparison module 132 can perform different alignment operations of the fingerprint images by using different alignment algorithms according to different application requirements. For example, the comparison module 132 can generate the first alignment result by comparing the geometric relationship of each fingerprint image with the geometric relationship of the preset fingerprint images. Therefore, the first comparison result corresponding to one fingerprint image may include a feature (or feature information) for indicating the same or similar between the fingerprint image and the preset fingerprint image. In this step, the processor 120 also executes the comparison module 132 to calculate an initial score corresponding to each fingerprint image according to the first comparison result. The comparison module 132 can calculate an initial score based on the first alignment result based on the employed alignment algorithm.

In this embodiment, the preset fingerprint image may be a fingerprint image that is pre-established according to the fingerprint of the user. For example, the storage device 130 of FIG. 1 is also used to record a fingerprint registration module (not shown). The processor 120 can execute the fingerprint registration module and the fingerprint sensor 110 can acquire one or more fingerprint images to generate a registered fingerprint image. In an embodiment, the processor 120 may execute a fingerprint processing module to perform an image processing operation on the fingerprint image captured by the fingerprint sensor 110, and generate a registered fingerprint image according to the image processed fingerprint image. . In addition, the processor 120 can execute the fingerprint registration module to combine the captured multiple fingerprint images into one registered fingerprint image, and store the registered fingerprint image into the storage device 130. However, in another embodiment, the fingerprint registration module may also separately store the captured fingerprint images into the storage device 130. In addition, in other embodiments, the preset fingerprint image may also be stored in a storage device external to the electronic device 10, and the electronic device 10 may obtain a preset fingerprint image through the network.

Next, in step S205, the processor 120 executes the comparison module 132 to compare each of the plurality of fingerprint images with each other to obtain at least one second comparison result. For example, the comparison module 132 can generate a second alignment result by comparing the geometric relationship of one fingerprint image with the geometric relationship of another fingerprint image. Therefore, the second alignment result corresponding to each of the two fingerprint images may include features (or feature information) for indicating the same or similar between the two fingerprint images. In other words, the first alignment result and the second alignment result can be used to indicate the degree of similarity between the two fingerprint images. When the image capturing module 131 captures two fingerprint images, the comparison module 132 can generate a second comparison result. When the image capturing module 131 captures more than three fingerprint images, the comparison module 132 can generate two or more second comparison results.

Then, in step S207, the processor 120 executes the verification module 133 to determine whether the plurality of fingerprint images pass the verification according to the plurality of first comparison results and the at least one second comparison result. In an embodiment, the processor 120 executes the verification module 133 to adjust the initial score calculated according to the first comparison result according to the second comparison result to generate a verification score corresponding to each fingerprint image. For example, in a case, the verification module 133 determines that the degree of similarity between two fingerprint images is high according to a certain second comparison result, and the verification module 133 separately sets the initial scores of the two fingerprint images. Increase to generate a verification score. In other words, the verification score in this case will be greater than the initial score. In another case, the verification module 133 determines that the degree of similarity between the two fingerprint images is not high enough according to a certain second comparison result, and the verification module 133 separately sets the initial scores of the two fingerprint images. Decrease to generate a verification score. In other words, the verification score in this other case will be smaller than the initial score.

In addition, in step S207, after obtaining the verification score, the processor 120 executes the verification module 133 to determine whether the verification score is higher than the verification threshold to determine whether the fingerprint image passes the verification. For example, the verification module 133 determines whether a plurality of verification scores include a verification score (also referred to as a first verification score) that meets the verification threshold. If it is determined that the plurality of verification scores include the first verification score, the fingerprint image image (also referred to as the first fingerprint image image) corresponding to the first verification score is determined to pass the verification. However, in another embodiment, the processor 120 executes the verification module 133 to determine whether the initial score is higher than the verification threshold to determine whether the initial score is to be adjusted according to the second comparison result. For example, in one case, the verification module 133 determines that the initial score of a certain fingerprint image is higher than the verification threshold, and thus directly determines that the fingerprint image passes the verification. In another case, the verification module 133 determines that the initial score of a certain fingerprint image is lower than the verification threshold, and thus adjusts the initial score according to the second comparison result corresponding to the fingerprint image to generate a new verification score. Then, based on the generated verification score, it is determined whether the fingerprint image passes the verification.

In an embodiment, before adjusting the initial score, the processor 120 may execute the comparison module 132 to generate at least one reference alignment result according to the first comparison result described above. For example, the comparison module 132 obtains the reference alignment result by comparing each of the two first alignment results. Then, the comparison module 132 can generate a similarity parameter according to the obtained reference comparison result and the second comparison result. Thereafter, the processor 120 may execute the verification module 133 to adjust the initial score according to the obtained similarity parameter to generate a verification score, and then determine whether the plurality of fingerprint images pass the verification according to the verification score.

FIG. 3 is a schematic diagram of a captured fingerprint image and a preset fingerprint image according to an embodiment of the invention.

Referring to FIG. 3 , the electronic device 10 executes the image capturing module 131 and detects multiple presses of the user by the fingerprint sensor 110 to capture a plurality of fingerprint images 321 , 322 , and 323 corresponding to the user fingerprint 30 . In the embodiment of FIG. 3, the preset fingerprint image 311 corresponding to the user fingerprint 30 has been stored in the storage device 130 of the electronic device 10. As shown in FIG. 3, the acquired fingerprint images 321, 322, and 323 and the preset fingerprint image 311 have overlapping regions, respectively. The overlapping area between the two fingerprint images includes the same or similar features (or feature information) between the two fingerprint images. In this embodiment, the processor 120 executes the comparison module 132 to find the overlapping area according to the geometric relationship of each fingerprint image. Further, the comparison module 132 generates a first comparison result corresponding to each fingerprint image 321 , 322 , 323 according to the overlapping area, and can calculate a corresponding result according to the first comparison result of each fingerprint image 321 , 322 , 323 . Initial score. Further, the acquired fingerprint images 321, 322, and 323 also have overlapping regions with each other. The processor 120 executes the comparison module 132 to generate a second comparison result between each of the fingerprint images 321 , 322 , 323 according to the overlapping area.

FIG. 4 is a schematic diagram of a fingerprint verification method according to an embodiment of the invention. In the embodiment of FIG. 4, the processor 120 executes the image capturing module 131 and obtains two fingerprint images by the fingerprint sensor 110 to perform a fingerprint verification operation.

Referring to FIG. 4, the processor 120 executes the image capturing module 131 to obtain fingerprint images 421 and 422. Then, the processor 120 performs a comparison module 132 to compare the fingerprint image 421 with the preset fingerprint image 411 to generate a comparison result CA(1), and compares the fingerprint image 422 with the preset fingerprint image 411 to generate a comparison result CA(1). Compare the results to CA(2). In addition, the comparison module 132 also compares the fingerprint image 421 with the fingerprint image 422 to generate a comparison result CB(1). Furthermore, the comparison module 132 further calculates an initial score of the corresponding fingerprint image 421 according to the comparison result CA(1), and calculates an initial score of the corresponding fingerprint image 422 according to the comparison result CA(2). After obtaining the above comparison result, the processor 120 executes the verification module 133 to determine whether the fingerprint image 421 and the fingerprint image 422 pass the verification based on the comparison result CA(1) and the comparison result CA(2).

Specifically, the processor 120 may first execute the comparison module 132 to generate a reference comparison result CR (1) between the fingerprint image 421 and the fingerprint image 422 according to the comparison result CA(1) and the comparison result CA(2). ). Further, the comparison module 132 obtains a similarity parameter based on the reference comparison result CR(1) and the comparison result CB(1) between the fingerprint image 421 and the fingerprint image 422. For example, the processor 120 performs a comparison between the geometric relationship of the corresponding fingerprint image 421 and the corresponding preset fingerprint image 411 by the comparison module 132 to obtain a ratio between the fingerprint image 421 and the preset fingerprint image 411. For the result CA(1). The comparison result CA(1) includes similarity information for indicating the same or similar feature (or feature information) between the fingerprint image 421 and the preset fingerprint image 411. Similarly, the comparison module 132 also compares the geometric relationship between the corresponding fingerprint image 422 and the corresponding preset fingerprint image 411 to obtain the comparison result CA between the fingerprint image 422 and the preset fingerprint image 411. ). The comparison result CA(2) includes similarity information for indicating the same or similar feature (or feature information) between the fingerprint image 422 and the preset fingerprint image 411. Then, the comparison module 132 compares the reference similarity information between the fingerprint image 421 and the fingerprint image 422 according to the similarity information of the comparison result CA(1) and the comparison result CA(2) as a reference comparison result. CR (1). The reference similarity information between the fingerprint image 421 and the fingerprint image 422 may be part of the similarity information between the fingerprint image 421 and the fingerprint image 422. For example, the comparison module 132 can analyze the same feature information between the two similarity information to obtain the reference similarity information. Further, the comparison module 132 determines the degree of similarity between the reference comparison result CR(1) between the fingerprint image 421 and the fingerprint image 422 and the comparison result CB(1) to obtain a similarity parameter. For example, the comparison module 132 may calculate the repetition rate of the similarity information of the reference comparison result CR(1) and the similarity information of the comparison result CB(1) as the similarity parameter.

After obtaining the similarity parameter, the processor 120 may execute the verification module 133 to adjust the initial score of the corresponding fingerprint image 421 according to the similarity parameter to generate a verification score corresponding to the fingerprint image 421, and adjust the corresponding fingerprint image according to the similarity parameter. The initial score of 422 is used to generate a verification score for the corresponding fingerprint image 422. In this embodiment, the verification module 133 determines how to adjust the initial score by determining whether the similarity parameter is less than a preset similarity threshold. For example, if it is determined that the similarity parameter is not less than (ie, equal to or greater than) the similarity threshold, the verification module 133 adjusts the initial score according to the first rule to generate a verification score. On the other hand, if it is determined that the similarity parameter is less than the similarity threshold, the verification module 133 adjusts the initial score according to the second rule to generate a verification score. In this embodiment, the verification score generated according to the first rule may be greater than or equal to the initial score, and the verification score generated according to the second rule may be smaller than the initial score.

Thereafter, the verification module 133 can determine whether the fingerprint images 421 and 422 pass the verification by determining whether the verification score meets the preset verification threshold. Here, the compliance threshold value refers to a value greater than or equal to the verification threshold. For example, when it is determined that the verification score of the corresponding fingerprint image 421 (or the fingerprint image 422) is greater than or equal to the verification threshold, the verification module 133 determines that the fingerprint image 421 (or the fingerprint image 422) passes the verification. When it is determined that the verification score of the corresponding fingerprint image 421 (or the fingerprint image 422) is less than the verification threshold, the verification module 133 determines that the fingerprint image 421 (or the fingerprint image 422) has not passed the verification. In this embodiment, the verification module 133 can determine that the current fingerprint verification result is verified by verification when one of the fingerprint image 421 and the fingerprint image 422 meets the verification threshold. However, in other embodiments, the verification module 133 can also determine that the fingerprint verification result is verified by the verification when both the fingerprint image 421 and the fingerprint image 422 meet the verification threshold.

FIG. 5 is a schematic diagram of a fingerprint verification method according to another embodiment of the invention. In the embodiment of FIG. 5, the processor 120 executes the image capturing module 131 and obtains three fingerprint images by the fingerprint sensor 110 to perform a fingerprint verification operation.

Referring to FIG. 5, similar to the method of the embodiment of FIG. 4, the processor 120 executes the image capturing module 131 to obtain fingerprint images 521, 522, and 523. Next, the processor 120 executes the comparison module 132 to compare the fingerprint images 521, 522, and 523 with the preset fingerprint image 511, respectively, and generates comparison results CA(3), CA(4), and CA(5). In addition, the comparison module 132 also compares the fingerprint image 521 with the fingerprint image 522 to generate a comparison result CB(2), compares the fingerprint image 522 with the fingerprint image 523 to generate a comparison result CB(3), and The fingerprint image 521 is compared with the fingerprint image 523 to produce a comparison result CB(4). Furthermore, the comparison module 132 calculates the initial scores of the corresponding fingerprint images 521, 522, and 523 based on the comparison results CA(3), CA(4), and CA(5), respectively.

In addition, the comparison module 132 further generates a reference comparison result CR(2) between the fingerprint image 521 and the fingerprint image 522 according to the comparison result CA(3) and the comparison result CA(4), according to the comparison result CA. (4) and the comparison result CA(5) to generate a reference comparison result CR(3) between the fingerprint image 522 and the fingerprint image 523, and according to the comparison result CA(3) and the comparison result CA(5) A reference comparison result CR(4) between the fingerprint image 521 and the fingerprint image 523 is generated. Further, the comparison module 132 can obtain a similarity parameter according to the reference comparison result CR(2) and the comparison result CB(2), according to the reference comparison result CR(3) and the comparison result CB(3). Another similarity parameter is obtained, and another similarity parameter is obtained based on the reference comparison result CR(4) and the comparison result CB(4).

In other words, in the embodiment of Figure 5, the fingerprint images 521, 522, 523 are associated with two similarity parameters, respectively. In this embodiment, the processor 120 may execute the verification module 133 to find the maximum similarity parameter among the similarity parameters associated with each fingerprint image, and then adjust the initial score of each fingerprint image according to the maximum similarity parameter. For example, the fingerprint image 521 is associated with the similarity parameter obtained by the reference comparison result CR(2) and the comparison result CB(2), and is also associated with the reference comparison result CR(4) and the comparison result CB ( 4) The similarity parameters obtained. It is assumed that the verification module 133 determines that the similarity parameter obtained by the reference comparison result CR(2) and the comparison result CB(2) is greater than that obtained by the reference comparison result CR(4) and the comparison result CB(4). Similarity parameter. Therefore, the verification module 133 adjusts the initial score of the fingerprint image 521 based on the similarity parameter obtained by the reference comparison result CR(2) and the comparison result CB(2) to generate a verification score. Further, the verification module 133 can determine the result of the fingerprint verification based on the verification score by a method similar to the embodiment of FIG.

In summary, the present invention performs a fingerprint verification operation by comparing a plurality of fingerprint images of a user to determine whether the verification result is a pass verification. Moreover, the fractional value between the obtained fingerprint image and the preset fingerprint image for indicating the comparison result may be adjusted according to the degree of similarity between each two fingerprint images. In this way, the reliability of the comparison result can be improved, thereby improving the accuracy of fingerprint verification.

Although the present invention has been disclosed in the above embodiments, it is not intended to limit the present invention, and any one of ordinary skill in the art can make some changes and refinements without departing from the spirit and scope of the present invention. The scope of the invention is defined by the scope of the appended claims.

10‧‧‧Electronic devices

110‧‧‧Finger sensor

120‧‧‧ processor

130‧‧‧Storage device

131‧‧‧Image capture module

132‧‧‧ Alignment module

133‧‧‧ verification module

S201, S203, S205, S207‧‧ steps

30‧‧‧ Fingerprint

311, 321, 322, 323, 411, 421, 422, 511, 521, 522, 523 ‧ ‧ fingerprint images

CA(1)~CA(5)‧‧‧ first comparison results

CB(1)~CB(4)‧‧‧Second alignment results

CR(1)~CR(4)‧‧‧ reference comparison results

FIG. 1 is a block diagram of an electronic device according to an embodiment of the invention. 2 is a flow chart of a fingerprint verification method according to an embodiment of the invention. FIG. 3 is a schematic diagram of a captured fingerprint image and a preset fingerprint image according to an embodiment of the invention. FIG. 4 is a schematic diagram of a fingerprint verification method according to an embodiment of the invention. FIG. 5 is a schematic diagram of a fingerprint verification method according to another embodiment of the invention.

Claims (10)

A fingerprint verification method includes: acquiring a plurality of fingerprint images; comparing each of the plurality of fingerprint images with a preset fingerprint image to obtain a plurality of first comparison results; Each of the two fingerprint images in the fingerprint image is compared with each other to obtain at least one second comparison result; and determining the plurality of fingerprint images according to the plurality of first comparison results and the at least one second comparison result Whether it passed the verification. The fingerprint verification method of claim 1, further comprising: generating a plurality of initial scores according to the plurality of first alignment results, wherein, according to the plurality of first alignment results, the at least one The step of determining, by the second comparison result, whether the plurality of fingerprint images pass the verification comprises: adjusting the plurality of initial scores according to the at least one second comparison result to obtain a plurality of verification scores; and according to the plurality of verifications The score determines whether the plurality of fingerprint images pass the verification. The fingerprint verification method of claim 2, wherein the step of determining whether the plurality of fingerprint images pass the verification according to the plurality of verification scores comprises: determining whether the plurality of verification scores include a verification threshold value At least one first verification score; and if it is determined that the plurality of verification scores include the at least one first verification score, determining one of the plurality of fingerprint images corresponding to the at least one first verification score The fingerprint image is verified. The fingerprint verification method of claim 2, further comprising: generating at least one reference comparison result according to the plurality of first alignment results; and comparing the at least one reference comparison result with the at least one The second comparison result obtains at least one similarity parameter, wherein the step of adjusting the plurality of initial scores according to the at least one second comparison result to obtain the plurality of verification scores comprises: according to the at least one similarity The parameter adjusts the plurality of initial scores to obtain the plurality of verification scores. The fingerprint verification method of claim 4, wherein the step of adjusting the plurality of initial scores according to the at least one similarity parameter to obtain the plurality of verification scores comprises: determining the at least one similarity parameter Whether it is less than a similarity threshold; if it is determined that the at least one similarity parameter is not less than the similarity threshold, the plurality of initial scores are adjusted according to a first rule to obtain the plurality of verification scores; If it is determined that the at least one similarity parameter is less than the similarity threshold, the plurality of initial scores are adjusted according to a second rule to obtain the plurality of verification scores. An electronic device includes: an image capture module for acquiring a plurality of fingerprint images; and a comparison module for comparing each of the plurality of fingerprint images with a predetermined fingerprint image Pairing a plurality of first alignment results, and comparing each of the plurality of fingerprint images to each other to obtain at least a second comparison result; and a verification module for And determining, by the plurality of first comparison results and the at least one second comparison result, whether the plurality of fingerprint images pass the verification. The electronic device of claim 6, wherein the comparison module is further configured to generate a plurality of initial scores according to the plurality of first alignment results, wherein the verification module is used according to the The at least one second comparison result adjusts the plurality of initial scores to obtain a plurality of verification scores, and determines whether the plurality of fingerprint images pass the verification according to the verification scores. The electronic device of claim 7, wherein the verification module is configured to determine whether the plurality of verification scores includes at least one first verification score that meets a verification threshold, wherein, if the The plurality of verification scores includes the at least one first verification score, and the verification module is configured to determine that a first fingerprint image of the plurality of fingerprint images corresponding to the at least one first verification score passes verification. The electronic device of claim 7, wherein the comparison module is configured to generate at least one reference comparison result according to the plurality of first alignment results, and compare the results according to the at least one reference. Acquiring at least one similarity parameter with the at least one second comparison result, wherein the verification module is configured to adjust the plurality of initial scores according to the at least one similarity parameter to obtain the plurality of verification scores. The electronic device of claim 9, wherein the verification module is configured to determine whether the at least one similarity parameter is less than a similarity threshold, wherein if the at least one similarity parameter is determined to be non- The verification module is configured to adjust the plurality of initial scores according to a first rule to obtain the plurality of verification scores; and wherein, if the at least one similarity parameter is determined The verification module is configured to adjust the plurality of initial scores according to a second rule to obtain the plurality of verification scores.