WO2017166318A1 - Fingerprint identification method and apparatus, and terminal - Google Patents

Abstract

A fingerprint identification method and apparatus, and a terminal. The fingerprint identification method comprises: acquiring m fingerprint sliding image sequences (201); respectively splicing the m fingerprint sliding image sequences into fingerprint images S1, S2,…, Sm (S202); intercepting fingerprint templates T1, T2,…, Tn from the fingerprint images S1, S2,…, Sm (S203); acquiring a fingerprint pressing image (S204); and comparing and matching the fingerprint pressing image with the fingerprint templates T1, T2,…, Tn (S205). According to the fingerprint identification method, by means of combining sliding registration with pressing identification, acquired fingerprint sliding image sequences are spliced into relatively large fingerprint images S1, S2,…, Sm after the sliding registration, and then fingerprint templates are intercepted from these fingerprint images for use in pressing identification. Thus, a user can complete fingerprint template registration by sliding a finger during registration, and fingerprint identification can be completed with one press during identification, which organically integrates the fingerprint identification solutions of the prior art.

Description

Fingerprint identification method, device and terminal Technical field

The present invention relates to the field of fingerprint recognition technologies, and in particular, to a fingerprint identification method, apparatus, and terminal.

Background technique

In recent years, with the popularization and application of mobile terminals such as smart phones, correspondingly, fingerprint recognition technology has also developed rapidly in the field of mobile terminals, involving functions such as fingerprint unlocking and fingerprint payment.

In the actual fingerprint application scenario, the user will face two fingerprint identification schemes: the first one is pressing registration, pressing recognition; the second is sliding registration, sliding recognition. The disadvantage of the first solution is that the fingerprint sensor registration fingerprint template is required to be pressed by the finger multiple times during registration, resulting in a poor user experience; the second disadvantage is that the finger needs to slide on the fingerprint sensor during recognition, and the fingerprint sensor is not pressed. Convenience.

Therefore, there is a need for a new fingerprint identification scheme that organically combines the above two schemes, retaining advantages to overcome disadvantages to enhance the user experience, and making minimal changes to the two fingerprint recognition schemes.

Summary of the invention

The embodiment of the invention provides a fingerprint identification method, which aims to organically integrate sliding registration and press recognition to enhance the user experience.

The first aspect provides a fingerprint identification method, including: acquiring m fingerprint sliding image sequences, where m is a natural number; and splicing the m fingerprint sliding image sequences into fingerprint images S1, S2, ..., Sm; Fingerprint images T1, T2, ..., Tn, n are extracted from the fingerprint images S1, S2, ..., Sm A natural number is obtained; a fingerprint pressing image is acquired; and the fingerprint pressing image is compared and matched with the fingerprint templates T1, T2, . . . , Tn.

In conjunction with the first aspect, in a first possible implementation manner of the first aspect, the intercepting the fingerprint templates T1, T2, ..., Tn from the fingerprint images S1, S2, ..., Sm includes: pressing a scan The size of the area is a search window, searching for the area with the largest effective area of the fingerprint in the horizontal direction of the fingerprint image Si, i traversing the integer in the interval [1, m]; and cutting the largest effective area of the fingerprint according to the size of the search window The area is used as the fingerprint template Tj, j is an integer in the interval [1, n]; the search window translates a preset number of pixels in the vertical direction of the fingerprint image Si, and the above steps are repeated, and finally the fingerprint template T1, T2 is intercepted. ,...,Tn.

In conjunction with the first possible implementation of the first aspect, in a second possible implementation of the first aspect, the preset number is greater than 1.

In conjunction with the first aspect, in a third possible implementation of the first aspect, the sliding scan area of the acquired fingerprint sliding image sequence is smaller than the pressed scanning area of the acquired fingerprint pressing image.

With reference to the first aspect and the foregoing implementation manner, in a fourth possible implementation manner of the first aspect, the method further includes: replacing the fingerprint pressing image with the fingerprint template Ts if the fingerprint pressing image is successfully matched with the fingerprint template Ts The fingerprint template Ts,s is an integer in the interval [1, n].

A second aspect provides a fingerprint identification device, comprising: an acquisition unit, configured to acquire m fingerprint sliding image sequences, where m is a natural number; and a splicing unit, configured to splicing the m fingerprint sliding image sequences into a fingerprint image S1 , S2, ..., Sm; intercepting unit, intercepting the fingerprint templates T1, T2, ..., Tn, n from the fingerprint images S1, S2, ..., Sm are natural numbers; the collecting unit is further configured to acquire a fingerprint pressing image; The identification unit is configured to compare and match the fingerprint pressing image with the fingerprint templates T1, T2, . . . , Tn.

In a third aspect, a terminal is provided, including: a housing, a processor, a memory, a circuit board, and an electric a source circuit, wherein the circuit board is disposed inside a space enclosed by the housing, the processor and the memory are disposed on the circuit board; the power supply circuit is configured to supply power to each circuit or device of the terminal; and the memory is configured to store the executable program code; The processor runs a program corresponding to the executable program code by reading executable program code stored in the memory for performing the following steps: acquiring m fingerprint sliding image sequences, m being a natural number; sliding the m fingerprints The image sequences are respectively spliced into fingerprint images S1, S2, ..., Sm; fingerprint templates T1, T2, ..., Tn, n are taken from the fingerprint images S1, S2, ..., Sm as natural numbers; fingerprint pressed images are acquired; The fingerprint pressing image is compared and matched with the fingerprint templates T1, T2, . . . , Tn.

In the embodiment of the present invention, the sliding registration and the pressing recognition are combined, and the captured sliding image sequence is spliced into larger fingerprint images S1, S2, . . . , Sm, and then intercepted in the fingerprint images for pressing identification. The fingerprint template, whereby the user can complete the fingerprint template registration by sliding the finger during registration, and only needs to press once to complete the fingerprint recognition, and organically integrates the fingerprint recognition scheme of the prior art.

The additional aspects and advantages of the invention will be set forth in part in the description which follows.

DRAWINGS

The above and/or additional aspects and advantages of the present invention will become apparent and readily understood from

1A and FIG. 1B are schematic diagrams showing the arrangement of a sliding fingerprint sensor and a push type fingerprint sensor according to an embodiment of the present invention;

2 is a flowchart of a fingerprint identification method according to Embodiment 1 of the present invention;

3 is a schematic diagram of a sequence of collected and stitched fingerprint sliding images provided by an embodiment of the present invention;

Figure 4 is a specific flow chart of step S203 of Figure 2;

FIG. 5 is a schematic diagram of intercepting a fingerprint image according to an embodiment of the present invention; FIG.

6 is a schematic diagram of a sliding scanning area and a pressing scanning area according to an embodiment of the present invention;

7 is a flowchart of a fingerprint identification method according to Embodiment 2 of the present invention;

FIG. 8 is a schematic structural diagram of a fingerprint identification apparatus according to Embodiment 3 of the present invention; FIG.

Figure 9 is a schematic structural view of the intercepting unit of Figure 8;

FIG. 10 is a schematic structural diagram of another fingerprint identification apparatus according to Embodiment 3 of the present invention; FIG.

FIG. 11 is a schematic structural diagram of a terminal according to Embodiment 4 of the present invention.

detailed description

The embodiments of the present invention are described in detail below, and the examples of the embodiments are illustrated in the accompanying drawings, in which the same or similar reference numerals indicate the same or similar modules or modules having the same or similar functions. The embodiments described below with reference to the accompanying drawings are intended to be illustrative of the invention and are not to be construed as limiting. Rather, the invention is to cover all modifications, modifications and equivalents within the spirit and scope of the appended claims.

In the field of mobile terminals, fingerprint recognition technology has been widely used. Taking the smartphone application scenario as an example, the user selects a finger to register on the smart phone according to his own usage habits, that is, the fingerprint sensor on the smart phone collects the fingerprint image of the user and saves it as a fingerprint template; subsequent users access the smart phone. When performing certain operations, such as fingerprint unlocking, fingerprint payment, etc., the fingerprint sensor on the smart phone collects the fingerprint image of the user in real time, and then matches it with the pre-saved fingerprint template. If the matching is successful, the user can perform corresponding operating. Depending on how the user operates during registration and identification, they can be divided into sliding and pressing. As shown in FIG. 1A, a strip-shaped sliding fingerprint sensor 11 is disposed on the front side of the smartphone; as shown in FIG. 1B, it is a square press. The fingerprint sensor is placed on the back of the smartphone.

In the embodiment of the present invention, the sliding fingerprint registration sequence is spliced into a larger fingerprint image after the sliding registration is combined with the sliding registration and the pressing recognition, and then the fingerprint template used for pressing recognition is intercepted in the fingerprint image. Therefore, the user can complete the fingerprint template registration by sliding the finger during registration, and only needs to press once to complete the fingerprint recognition, and organically integrates the fingerprint recognition scheme of the prior art.

FIG. 2 is a flowchart of a fingerprint identification method according to Embodiment 1 of the present invention. As shown in Figure 2, the method includes:

S201: Obtain m fingerprint sliding image sequences, where m is a natural number.

In the embodiment of the present invention, the sliding mode is adopted at the time of registration. When the finger slides over the fingerprint sensor, the sliding scanning area on the fingerprint sensor scans the slipped finger at a certain frequency, and collects a series of fingerprint sliding images with a relatively small area relative to the finger, as shown in FIG. Slide the image sequence for the fingerprint. The size of each fingerprint sliding image is based on the size of the sliding scanning area. As shown in FIG. 3, the size of the sliding scanning area is W*Hs pixels, and the size of each fingerprint sliding image is also W*Hs pixels.

It should be noted that a fingerprint sliding image sequence obtained by sliding a finger on the fingerprint sensor once, each fingerprint sliding image sequence includes multiple fingerprint sliding images; and multiple sliding sliding image sequences can be collected. In the embodiment of the present invention, m=1 is taken as an example for description.

S202: splicing the m fingerprint sliding image sequences into fingerprint images S1, S2, . . . , Sm.

In the embodiment of the present invention, when m=1, a fingerprint sliding image sequence is spliced into a larger fingerprint image S1, and the fingerprint image S1 reflects fingerprint texture information in a larger area of the finger. When m=2, the fingerprint sliding image sequence obtained by the first sliding is spliced into the fingerprint image S1, and the fingerprint sliding image sequence obtained by the second sliding is spliced into the fingerprint image S2; and so on, when m is greater than 2, The m fingerprint sliding image sequences are respectively spliced into fingerprint images S1, S2, ..., Sm. S1, S2, ..., Sm all reflect the fingerprint texture information in a large area of the finger, but the fingerprint texture information contained therein is different.

The splicing method here can adopt the existing splicing algorithm. Due to the possibility of offset during splicing, as shown in FIG. 3, the size of the fingerprint image S1 is Width*Height pixels, the Width is greater than W, and the Height is greater than Hs.

S203: The fingerprint templates T1, T2, ..., Tn, n are extracted from the fingerprint images S1, S2, ..., Sm as natural numbers.

Since only a small area of fingerprint texture information is required at the time of press recognition, a large area of fingerprint texture information such as the fingerprint image S1 is not required. In the embodiment of the present invention, a plurality of small areas are cut out from the fingerprint image S1. Fingerprint image. As an embodiment of the present invention, as shown in FIG. 4, S203 specifically includes the following steps:

S401: Searching for the size of the pressed scan area as a search window, searching for the area with the largest effective area of the fingerprint in the horizontal direction of the fingerprint image Si, i traversing the integer in the interval [1, m].

When the recognition is pressed, the size of the fingerprint template saved in advance should be the same as the size of the fingerprint compression image collected when the finger is pressed, and the size of the fingerprint compression image is based on the size of the pressed scanning area. In the embodiment of the present invention, the size of the pressed scan area (W*H pixel) is used as the search window, and m=1, and the area with the largest effective area of the fingerprint is searched in the horizontal direction of the fingerprint image S1, as shown in FIG. The direction is in the direction of Width.

S402: The area with the largest effective area of the fingerprint is intercepted according to the size of the search window as the fingerprint template Tj, and j is an integer in the interval [1, n].

Each time after searching in the horizontal direction, an area with the largest effective area of the fingerprint is obtained, and it is intercepted as a fingerprint template, such as the fingerprint template T1 in FIG.

S403: The search window translates a preset number of pixels in a vertical direction of the fingerprint image Si, and then repeats the above steps, and finally extracts the fingerprint templates T1, T2, . . . , Tn.

Each time after searching for a fingerprint template in the horizontal direction, the search window shifts a preset number of pixels in the vertical direction, the vertical direction is in the Height direction, and then the process of searching and intercepting is repeated in the horizontal direction, thereby obtaining a plurality of fingerprint templates T2, ... , Tn.

In the embodiment of the present invention, the fingerprint template is extracted from the fingerprint large image (fingerprint image S1) spliced during the sliding registration, and the size of the fingerprint template is the same as the size of the fingerprint pressing image during the recognition, so that the sliding registration and the pressing recognition can be effectively performed. Connect.

In view of the correlation of the fingerprint template obtained by the truncation, as one embodiment of the present invention, the number of pixels in the search window that are translated in the vertical direction is greater than one. That is, when the image is translated in the vertical direction, the adjacent search windows may be overlapped or non-overlapping. For example, if the size of the search window is W*H pixels, the preset number of panning is less than or equal to H when overlapped, and the preset number of pans is greater than H when there is no overlap.

S204: Acquire a fingerprint pressing image.

In the recognition, the pressing method is adopted: the finger is pressed on the fingerprint sensor, and the pressed scanning area on the fingerprint sensor scans the pressed finger at a certain frequency to collect a fingerprint pressing image. The size of the fingerprint pressing image is based on the size of the pressing scanning area. As shown in FIG. 6 , the size of the pressing scanning area is W*H pixels, and the size of the fingerprint pressing image is also W*H pixels.

As an embodiment of the present invention, the sliding scan area for acquiring the fingerprint sliding image sequence is smaller than the pressing scanning area for acquiring the fingerprint pressing image. This is because when sliding registration, there is a slight relative movement between the finger and the sliding scanning area, and a certain deformation is introduced when splicing into the fingerprint image S1. At the same scanning frequency, the smaller the sliding scanning area is, the more deformation is generated. small.

S205: Compare and match the fingerprint pressing image with the fingerprint templates T1, T2, . . . , Tn.

In the embodiment of the present invention, combined with sliding registration and press recognition, the sliding registration will be obtained. The fingerprint sliding image sequence is spliced into a larger fingerprint image S1, and then the fingerprint template used for pressing recognition is taken out in the fingerprint image, thereby the user can complete the registration of the fingerprint template by sliding the finger during registration, when identifying Fingerprint recognition can be completed only by pressing once, and the fingerprint recognition scheme of the prior art is organically integrated.

As a preferred embodiment of the present invention, when sliding registration, the finger slides on the fingerprint sensor multiple times, and a plurality of fingerprint sliding image sequences are acquired, that is, m is greater than 1. Each fingerprint sliding image sequence is respectively spliced into a fingerprint large image (fingerprint image S1, S2, ..., Sm), and then the fingerprint image S1, S2, ..., Sm is subjected to the search and interception steps described above, and the fingerprint template T1 is intercepted. , T2,...,Tn,... The multiple fingerprint sliding image sequences are collected during the sliding registration because the relative position of the finger and the sliding scanning area is shifted to different degrees each time the sliding is performed, and the fingerprinted large image is obtained (fingerprint images S1, S2, ... , Sm) is not the same, that is, each time the fingerprint texture information collected is not the same, more fingerprint templates can be intercepted from multiple fingerprint large images, including more fingerprint texture information, which is beneficial to the subsequent identification process. .

FIG. 7 is a flowchart of a fingerprint identification method according to Embodiment 2 of the present invention. As shown in FIG. 7, the method includes:

S701-S705: The steps are the same as those of the foregoing S201-S205, and details are not described herein again.

S706: If the fingerprint pressing image and the fingerprint template Ts are successfully matched, the fingerprint template Ts is replaced by the fingerprint pressing image, and s is an integer in the interval [1, n].

In the embodiment of the present invention, the cut fingerprint template is T1, T2, . . . , Tn. If the captured fingerprint pressing image matches the fingerprint template Ts successfully, the fingerprint template Ts is replaced by the fingerprint pressing image. The matching method here can adopt an existing fingerprint image recognition algorithm, and judge whether the fingerprint pressing image and the fingerprint template match according to the magnitude of the similarity. The similarity represents a degree of similarity between images, including but not limited to the number of feature point matches, the histogram distribution similarity, and the like. The greater the similarity, the graph The probability that the match is successful and recognized is greater.

The fingerprint template obtained by the sliding is replaced by the fingerprint pressing image because: compared with the fingerprint pressing image, the fingerprint template obtained by splicing and cutting the fingerprint sliding sequence has a certain deformation, thereby affecting the recognition rate; after each recognition is successful, The fingerprint pressing image replaces the fingerprint template obtained by sliding, and the fingerprint template obtained by sliding can be gradually replaced with the fingerprint template obtained by pressing, thereby reducing the influence of deformation and improving the recognition rate, and at the same time, the user is not required to perform additional Operation.

FIG. 8 is a schematic structural diagram of a fingerprint identification apparatus according to Embodiment 3 of the present invention. As shown in FIG. 8, the fingerprint identification device 80 includes an acquisition unit 81, a splicing unit 82, a clipping unit 83, and an identification unit 84.

The collecting unit 81 is located in the sensing area of the fingerprint sensor, and is used to acquire m fingerprint sliding image sequences, where m is a natural number.

The splicing unit 82 is configured to splicing the m fingerprint sliding image sequences into fingerprint images S1, S2, . . . , Sm, respectively.

The intercepting unit 83 intercepts the fingerprint templates T1, T2, ..., Tn, n from the fingerprint images S1, S2, ..., Sm as natural numbers.

The collecting unit 81 is further configured to acquire a fingerprint pressing image.

The identification unit 84 is configured to compare and match the fingerprint pressing image with the fingerprint templates T1, T2, . . . , Tn.

Preferably, as shown in FIG. 9, the intercepting unit 83 includes a search subunit 831, a truncation subunit 832, and a panning subunit 833.

The search sub-unit 831 is configured to search for the area where the effective area of the fingerprint is the largest in the horizontal direction of the fingerprint image Si by using the size of the pressed scan area as the search window, i traversing the integer in the interval [1, m].

The intercepting sub-unit 832 is configured to intercept the area with the largest effective area of the fingerprint as the fingerprint template Tj according to the size of the search window, and j is an integer in the interval [1, n].

The translation sub-unit 833 is configured to translate the search window by a preset number of pixels in the vertical direction of the fingerprint image Si, and then repeat the operations of the search sub-unit 831 and the intercept sub-unit 832, and finally intercept the fingerprint templates T1, T2, . . . , Tn.

In the embodiment of the present invention, the fingerprint template is extracted from the fingerprint large image (fingerprint image S1, S2, ..., Sm) obtained by splicing during the sliding registration, and the size of the fingerprint template is the same as the size of the fingerprint pressing image during the recognition, so that the sliding can be performed. Registration and press recognition are effectively articulated.

As an embodiment of the present invention, the preset number of translations of the search window in the vertical direction is greater than one in consideration of the correlation of the fingerprint templates obtained by the interception. That is, when the image is translated in the vertical direction, the adjacent search windows may be overlapped or non-overlapping.

As another embodiment of the present invention, the sliding scan area in the acquisition unit 81 is smaller than the pressed scan area. This is because when sliding registration, there is a slight relative movement between the finger and the sliding scanning area, and a certain deformation is introduced when splicing into the fingerprint images S1, S2, ..., Sm, and the scanning area is scanned at the same scanning frequency. The smaller the smaller the deformation, the smaller.

As still another embodiment of the present invention, as shown in FIG. 10, the fingerprint identification device 80 further includes a replacement unit 85 for replacing the fingerprint template Ts with the fingerprint pressing image if the fingerprint pressing image matches the fingerprint template Ts successfully. s is an integer in the interval [1, n].

The fingerprint template obtained by the sliding is replaced by the fingerprint pressing image because: compared with the fingerprint pressing image, the fingerprint template obtained by splicing and cutting the fingerprint sliding sequence has a certain deformation, thereby affecting the recognition rate; after each recognition is successful, The fingerprint pressing image replaces the fingerprint template obtained by sliding, and the fingerprint template obtained by sliding can be gradually replaced with the fingerprint template obtained by pressing, thereby reducing the influence of deformation and improving the recognition rate, and at the same time, the user is not required to perform additional Fuck Work.

In the embodiment of the present invention, the sliding fingerprint registration sequence is spliced into a larger fingerprint image S1, S2, ..., Sm after the sliding registration is combined with the sliding registration and the pressing recognition, and then the fingerprint images are intercepted in the fingerprint images. Pressing the fingerprint template used for identification, the user can complete the fingerprint template registration by sliding the finger during registration, and only needs to press once to complete the fingerprint recognition, and organically integrates the fingerprint recognition scheme of the prior art.

It is to be understood that the device in this embodiment corresponds to the foregoing method embodiment. Therefore, the specific content of each module of the device in this embodiment can be referred to the related description in the method embodiment, and is not described in detail herein.

FIG. 11 is a schematic structural diagram of a terminal according to Embodiment 4 of the present invention. As shown in FIG. 11, the terminal 1100 includes a housing 1101, a processor 1102, a memory 1103, a circuit board 1104, and a power supply circuit 1105. The circuit board 1104 is disposed inside a space surrounded by the housing 1101, and the processor 1102 and The memory 1103 is disposed on the circuit board 1104; the power supply circuit 1105 is for supplying power to the respective circuits or devices of the terminal 1100; the memory 1103 is for storing executable program code; and the processor 1102 is configured to read the executable program code stored in the memory 1103. Run the program corresponding to the executable code to perform the following steps:

Obtain m fingerprint sliding image sequences, where m is a natural number.

The m fingerprint sliding image sequences are respectively spliced into fingerprint images S1, S2, ..., Sm.

The fingerprint templates T1, T2, ..., Tn, n are taken from the fingerprint images S1, S2, ..., Sm as natural numbers.

Get the fingerprint pressed image.

The fingerprint pressing image is compared and matched with the fingerprint templates T1, T2, ..., Tn.

In the embodiment of the present invention, combined with sliding registration and press recognition, the sliding registration will be obtained. The fingerprint sliding image sequence is spliced into larger fingerprint images S1, S2, ..., Sm, and then the fingerprint template used for pressing recognition is taken out in the fingerprint images, thereby the user can complete the fingerprint template by sliding the finger during registration. The registration can be completed only by pressing once, and the fingerprint recognition scheme of the prior art is organically integrated.

It should be noted that any process or method description in the flowcharts or otherwise described herein can be understood as representing code that includes one or more executable instructions for implementing the steps of a particular logical function or process. Modules, segments or portions, and the scope of the preferred embodiments of the invention includes additional implementations, which may not be in the order shown or discussed, including in a substantially simultaneous manner or in reverse order depending on the functionality involved. The functions are performed, which should be understood by those skilled in the art to which the embodiments of the present invention pertain.

It should be understood that portions of the invention may be implemented in hardware, software, firmware or a combination thereof. In the above-described embodiments, multiple steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented by any one or combination of the following techniques well known in the art: having logic gates for implementing logic functions on data signals. Discrete logic circuits, application specific integrated circuits with suitable combinational logic gates, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), etc.

One of ordinary skill in the art can understand that all or part of the steps carried by the method of implementing the above embodiments can be completed by a program to instruct related hardware, and the program can be stored in a computer readable storage medium. When executed, one or a combination of the steps of the method embodiments is included.

In addition, each functional unit in each embodiment of the present invention may be integrated into one processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. In the block. The above integrated modules can be implemented in the form of hardware or in the form of software functional modules. The integrated modules, if implemented in the form of software functional modules and sold or used as stand-alone products, may also be stored in a computer readable storage medium.

The above mentioned storage medium may be a read only memory, a magnetic disk or an optical disk or the like.

Although the embodiments of the present invention have been shown and described, it is understood that the above-described embodiments are illustrative and are not to be construed as limiting the scope of the invention. The embodiments are subject to variations, modifications, substitutions and variations.

Claims (11)

A fingerprint identification method, comprising: Obtaining m fingerprint sliding image sequences, where m is a natural number; Splicing the m fingerprint sliding image sequences into fingerprint images S1, S2, ..., Sm; Extracting fingerprint templates T1, T2, ..., Tn, n from the fingerprint images S1, S2, ..., Sm are natural numbers; Obtaining a fingerprint pressing image; The fingerprint pressing image is compared and matched with the fingerprint templates T1, T2, . . . , Tn. The method according to claim 1, wherein the intercepting the fingerprint templates T1, T2, ..., Tn from the fingerprint images S1, S2, ..., Sm comprises: Searching for the size of the scan area, searching for the area with the largest effective area of the fingerprint in the horizontal direction of the fingerprint image Si, i traversing the integer in the interval [1, m]; Obtaining, according to the size of the search window, an area where the effective area of the fingerprint is the largest as a fingerprint template Tj, j is an integer in the interval [1, n]; The search window translates a preset number of pixels in the vertical direction of the fingerprint image Si, repeats the above steps, and finally intercepts the fingerprint templates T1, T2, . . . , Tn. The method of claim 2 wherein: The preset number is greater than one. The method of claim 1 wherein The sliding scan area of the fingerprint sliding image sequence is smaller than the pressing scanning area of the fingerprint pressing image. The method according to any one of claims 1 to 4, wherein the method further comprises: If the fingerprint pressing image is successfully matched with the fingerprint template Ts, the fingerprint template Ts is replaced with the fingerprint pressing image, and s is an integer within the interval [1, n]. A fingerprint identification device, comprising: The acquiring unit is configured to acquire m fingerprint sliding image sequences, where m is a natural number; a splicing unit, configured to splicing the m fingerprint sliding image sequences into fingerprint images S1, S2, ..., Sm; The intercepting unit intercepts the fingerprint templates T1, T2, . . . , Tn, n from the fingerprint images S1, S2, . . . , Sm; The collecting unit is further configured to acquire a fingerprint pressing image; The identification unit is configured to compare and match the fingerprint pressing image with the fingerprint templates T1, T2, . . . , Tn. The apparatus according to claim 6, wherein the intercepting unit comprises: Searching the subunit for searching the size of the scan area, searching for the area with the largest effective area of the fingerprint in the horizontal direction of the fingerprint image Si, i traversing the integer in the interval [1, m]; The intercepting subunit is configured to intercept, according to the size of the search window, an area with the largest effective area of the fingerprint as a fingerprint template Tj, where j is an integer in the interval [1, n]; a panning subunit for translating the search window in a vertical direction of the fingerprint image Si by a preset number of pixels, so that the search subunit and the truncating subunit are cyclically operated, and finally the fingerprint template T1 is intercepted. T2,...,Tn. The device of claim 7 wherein: The preset number is greater than one. The device of claim 6 wherein: The sliding scanning area in the collecting unit is smaller than the pressing scanning area. The device according to any one of claims 6-9, wherein the device further comprises: And a replacing unit, configured to replace the fingerprint template Ts with the fingerprint pressing image as an integer in the interval [1, n] if the fingerprint pressing image is successfully matched with the fingerprint template Ts. A terminal includes: a housing, a processor, a memory, a circuit board, and a power supply circuit, wherein the circuit board is disposed inside the space enclosed by the housing, the processor and the memory are disposed on the circuit board; and the power circuit is configured to Each circuit or device of the terminal is powered; the memory is for storing executable program code; the processor runs the program corresponding to the executable program code by reading executable program code stored in the memory for performing the following steps: Obtaining m fingerprint sliding image sequences, where m is a natural number; Splicing the m fingerprint sliding image sequences into fingerprint images S1, S2, ..., Sm; Extracting fingerprint templates T1, T2, ..., Tn, n from the fingerprint images S1, S2, ..., Sm are natural numbers; Obtaining a fingerprint pressing image; The fingerprint pressing image is compared and matched with the fingerprint templates T1, T2, . . . , Tn.

Images