CN117456571A

CN117456571A - Fingerprint identification method and electronic equipment

Info

Publication number: CN117456571A
Application number: CN202311773169.6A
Authority: CN
Inventors: 谢字希; 邸皓轩; 李丹洪
Original assignee: Honor Device Co Ltd
Current assignee: Honor Device Co Ltd
Priority date: 2023-12-21
Filing date: 2023-12-21
Publication date: 2024-01-26

Abstract

The embodiment of the application is applied to the technical field of fingerprint identification and provides a fingerprint identification method and electronic equipment. And responding to touch operation of a user on a fingerprint acquisition area of the electronic equipment, and acquiring a fingerprint restoration image by the electronic equipment, wherein the fingerprint restoration image is an image generated after the fingerprint verification image acquired by the electronic equipment is restored. And then, the electronic equipment judges whether a fingerprint template matched with the fingerprint restoration image exists in the fingerprint template library. Then, in the case that a fingerprint template matched with the fingerprint repair image exists in the fingerprint template library, the electronic device updates the fingerprint verification image and/or the fingerprint repair image into the fingerprint template library. In this application, can promote fingerprint identification's success rate.

Description

Fingerprint identification method and electronic equipment

Technical Field

The application relates to the technical field of fingerprint identification, in particular to a fingerprint identification method and electronic equipment.

Background

Along with development of information identification technology, the electronic equipment is more mature in the scene of fingerprint input and fingerprint unlocking based on the fingerprint identification technology. However, in an actual usage scenario, the quality of the collected fingerprint image is generally low due to the fact that the finger is in a special state (such as a dry finger, a low-temperature finger, a wet finger, etc.), so that the fingerprint recognition rate is greatly reduced, and the usage experience of a user is finally affected.

Disclosure of Invention

The embodiment of the application provides a fingerprint identification method and electronic equipment, which are used for improving the success rate of fingerprint identification rate.

In order to achieve the above purpose, the embodiments of the present application adopt the following technical solutions:

in a first aspect, a fingerprint identification method is provided, in which, in response to a touch operation of a user on a fingerprint collection area of an electronic device, the electronic device obtains a fingerprint restoration image, where the fingerprint restoration image is an image generated after a fingerprint verification image collected by the electronic device is restored. And then, the electronic equipment judges whether a fingerprint template matched with the fingerprint restoration image exists in a fingerprint template library, wherein the fingerprint template library comprises at least one fingerprint template. Then, in the case that a fingerprint template matched with the fingerprint repair image exists in the fingerprint template library, the electronic device updates the fingerprint verification image and/or the fingerprint repair image into the fingerprint template library.

In the embodiment of the invention, the electronic device can determine whether the fingerprint template library can be updated by judging whether the fingerprint template matched with the fingerprint restoration image exists in the fingerprint template library, if the fingerprint template matched with the fingerprint restoration image exists in the fingerprint template library, the electronic device can add or replace the fingerprint verification image and/or the fingerprint restoration image into the fingerprint template library, so that the fingerprint template library not only comprises the fingerprint image before restoration, but also comprises the fingerprint image after restoration, further fingerprint identification under different restoration conditions is realized, not only can the unlocking efficiency of the electronic device be improved, the occurrence of the situation that a user needs to unlock for many times due to the unlocking failure of the electronic device is reduced, but also the unlocking precision of the electronic device is improved, the occurrence of the situation that the unlocking failure of the electronic device is caused due to the conditions of dry fingers, wet fingers, low-temperature fingers and the like is reduced, the success rate of fingerprint identification of the electronic device is improved, and the use experience of the user is further improved.

In a possible implementation manner of the first aspect, the process of updating the fingerprint template library by the electronic device may specifically include: under the condition that the fingerprint verification image meets a first preset condition, the electronic equipment updates the fingerprint verification image into a fingerprint template library; the first preset condition comprises at least one of an overlapping area between the fingerprint verification image and the target fingerprint template being larger than a preset area, a matching value of the fingerprint verification image and the target fingerprint template being larger than a first preset matching value, and a first combination value being larger than a first preset combination value; the target fingerprint template is the fingerprint template with the highest matching value with the fingerprint verification image in the fingerprint template library; the first combined value is determined based on the overlap area and the matching value.

In this application, the electronic equipment updates the fingerprint image before restoration (or refer to fingerprint verification image) to fingerprint template storehouse in, can promote the efficiency of electronic equipment fingerprint identification, that is to say, the electronic equipment reacquires similar fingerprint verification image next time, need not to restore through the fingerprint restoration model, just can realize fingerprint identification, so, not only can reduce the calculated amount of electronic equipment, promote the performance of electronic equipment, promote the efficiency of electronic equipment fingerprint identification moreover, provide convenience for follow-up electronic equipment carries out fingerprint identification.

In a possible implementation manner of the first aspect, the method further includes: under the condition that the overlapping area between the fingerprint verification image and the target fingerprint template is larger than the preset area, the electronic equipment determines that the fingerprint verification image meets a first preset condition; or under the condition that the overlapping area between the fingerprint verification image and the target fingerprint template is smaller than or equal to the preset area, the electronic device determines that the fingerprint verification image does not meet the first preset condition.

In the application, if the overlapping area is larger than the preset area, the fingerprint verification image and the fingerprint image prestored by the electronic equipment are the fingerprint image of the same user, and the electronic equipment can determine that the fingerprint verification image meets the first preset condition; if the overlapping area is smaller than or equal to the preset area, the fact that the fingerprint verification image possibly has fingerprint deletion compared with the fingerprint image stored in advance by the electronic equipment is indicated, and the electronic equipment determines that the fingerprint verification image does not meet the first preset condition, so that the integrity of the fingerprint image in the fingerprint template can be ensured, and a foundation is provided for subsequent fingerprint identification.

In a possible implementation manner of the first aspect, the method further includes: under the condition that the matching value of the fingerprint verification image and the target fingerprint template is larger than a first preset matching value, the electronic equipment determines that the fingerprint verification image meets a first preset condition; or under the condition that the matching value of the fingerprint verification image and the target fingerprint template is smaller than or equal to a first preset matching value, the electronic equipment determines that the fingerprint verification image does not meet the first preset condition.

In the application, if the matching value is greater than the first preset matching value, it indicates that the fingerprint verification image is substantially the same as the fingerprint image stored in advance by the electronic device, so that the electronic device can determine that the fingerprint verification image meets the first preset condition, that is, the electronic device can update the fingerprint verification image into the fingerprint template library. If the matching value is smaller than or equal to the first preset matching value, the fingerprint verification image is matched with the fingerprint image stored in the electronic device in advance, but the fingerprint verification image does not reach the same fingerprint template, so that the electronic device can determine that the fingerprint verification image does not meet the first preset condition. Therefore, not only can the occurrence of the situation of excessively occupying the storage space be reduced, but also the basis can be provided for the subsequent fingerprint identification.

In a possible implementation manner of the first aspect, the process of determining, by the electronic device, the first combined value may specifically include: the electronic device calculates a first product between the first weight and the matching value, and calculates a second product between the second weight and the overlapping area. Then, the electronic device adds the first product and the second product to obtain a first combined value.

In a possible implementation manner of the first aspect, the method further includes: under the condition that the first combination value is larger than a first preset combination value, the electronic equipment determines that the fingerprint verification image meets a first preset condition; or, in the case that the first combination value is smaller than or equal to the first preset combination value, the electronic device determines that the fingerprint verification image does not satisfy the first preset condition.

In the application, if the first combination value is greater than the first preset combination value, it is indicated that the fingerprint verification image meets the template updating condition, so that the electronic device can determine that the fingerprint verification image meets the first preset condition. If the first combination value is smaller than or equal to a first preset combination value, the fingerprint verification image is not in accordance with the template updating condition, so that the electronic equipment determines that the fingerprint verification image is not in accordance with the first preset condition. Therefore, the fingerprint image which does not accord with the template updating condition can be prevented from being updated into the fingerprint template library, so that the occurrence probability of trouble to follow-up fingerprint identification is reduced, and a foundation is provided for follow-up fingerprint identification successfully by the electronic equipment.

In a possible implementation manner of the first aspect, the method further includes: and under the condition that the overlapping area between the fingerprint verification image and the target fingerprint template is larger than the preset area, the matching value of the fingerprint verification image and the target fingerprint template is larger than the first preset matching value and the first combined value is larger than the first preset combined value, the electronic equipment determines that the fingerprint verification image meets the first preset condition.

In the application, the electronic device may determine whether the above-mentioned matching value is greater than a first preset matching value, if the matching value is greater than the first preset matching value, the electronic device may continuously determine whether the above-mentioned overlapping area is greater than a preset area, if the overlapping area is greater than the preset area, the electronic device may determine whether the first combination value is greater than the first preset combination value, and if the first combination value is greater than the first preset combination value, the electronic device may determine that the fingerprint verification image satisfies the first preset condition. Therefore, the occurrence of the condition that the success rate of fingerprint matching is reduced due to image quality can be reduced, the rejection rate is reduced, the false recognition caused by the problem of matching values can be avoided, and the use experience of a user is improved.

In a possible implementation manner of the first aspect, the process of updating the fingerprint template library by the electronic device may specifically include: under the condition that the fingerprint repair image meets a second preset condition, the electronic equipment updates the fingerprint repair image into a fingerprint template library; the second preset condition comprises at least one of a mass fraction of the fingerprint restoration image being greater than a preset fraction, a highest matching value of the fingerprint restoration image corresponding to a fingerprint template in the fingerprint template library being greater than a second preset matching value, and a second combined value being greater than a second preset combined value; the second combined value is determined based on the quality score and the highest matching value.

In this application, the electronic equipment is with the fingerprint image after the restoration (or refer to fingerprint restoration image) update to fingerprint template storehouse in, can make the image quality of every fingerprint template in the fingerprint template storehouse all reach the quality requirement of predetermineeing, and then can promote fingerprint identification's precision, reduce the electronic equipment misidentification or miss the condition emergence of discernment, promote user's use experience.

In a possible implementation manner of the first aspect, the method further includes: under the condition that the quality fraction of the fingerprint repair image is larger than the preset fraction, the electronic equipment determines that the fingerprint repair image meets a second preset condition; or under the condition that the quality score of the fingerprint repair image is smaller than or equal to the preset score, the electronic equipment determines that the fingerprint repair image does not meet the second preset condition.

In the application, if the quality score of the fingerprint repair image is greater than the preset score, it is indicated that the image quality of the fingerprint repair image is higher, so that the electronic device can determine that the fingerprint repair image meets the second preset condition. If the quality score of the fingerprint repair image is smaller than or equal to the preset score, the fingerprint repair image is lower in image quality, and the electronic equipment determines that the fingerprint repair image does not meet a second preset condition. Therefore, the quality of the fingerprint templates in the fingerprint template library can be ensured, and a foundation is provided for successful fingerprint identification of subsequent electronic equipment.

In a possible implementation manner of the first aspect, the method further includes: under the condition that the highest matching value corresponding to the fingerprint template in the fingerprint repair image and the fingerprint template library is larger than a second preset matching value, the electronic equipment determines that the fingerprint repair image meets a second preset condition; or under the condition that the highest matching value corresponding to the fingerprint template in the fingerprint repair image and the fingerprint template library is smaller than or equal to the second preset matching value, the electronic equipment determines that the fingerprint repair image does not meet the second preset condition.

In the application, if the highest matching value is greater than the second preset matching value, it is indicated that the fingerprint repair image is basically the same as the fingerprint image prestored by the electronic device, so that the electronic device can determine that the fingerprint repair image meets the second preset condition. If the highest matching value is smaller than or equal to the second preset matching value, the fingerprint restoration image is matched with the fingerprint image stored in the electronic device in advance, but the requirement of updating the fingerprint restoration image into the fingerprint template library is not met, so that the electronic device can determine that the fingerprint restoration image does not meet the second preset condition. Therefore, not only can the occurrence of the situation of excessively occupying the storage space be reduced, but also the basis can be provided for the subsequent fingerprint identification.

In a possible implementation manner of the first aspect, the process of determining, by the electronic device, the second combined value may specifically include: the electronic device calculates a third product between the third weight and the highest matching value and calculates a fourth product between the fourth weight and the quality score. The electronic device may then add the third product to the fourth product to obtain a second combined value.

In a possible implementation manner of the first aspect, the method further includes: under the condition that the second combination value is larger than a second preset combination value, the electronic equipment determines that the fingerprint restoration image meets a second preset condition; or under the condition that the second combination value is smaller than or equal to a second preset combination value, the electronic equipment determines that the fingerprint repair image does not meet the second preset condition.

In the application, if the second combination value is greater than the second preset combination value, it is indicated that the fingerprint repair image meets the template updating condition, so that the electronic device can determine that the fingerprint repair image meets the second preset condition. If the second combination value is smaller than or equal to a second preset combination value, the fingerprint restoration image is not in accordance with the template updating condition, so that the electronic equipment determines that the fingerprint restoration image is not in accordance with the second preset condition. Therefore, the fingerprint image which does not accord with the template updating condition can be prevented from being updated into the fingerprint template library, so that the occurrence probability of trouble to follow-up fingerprint identification is reduced, and a foundation is provided for follow-up fingerprint identification successfully by the electronic equipment.

In a possible implementation manner of the first aspect, the method further includes: and under the condition that the quality score of the fingerprint restoration image is larger than a preset score, the highest matching value corresponding to the fingerprint template in the fingerprint template library of the fingerprint restoration image is larger than a second preset matching value, and the second combination value is larger than a second preset combination value, the electronic equipment determines that the fingerprint restoration image meets a second preset condition.

In the application, the electronic device may determine whether the highest matching value is greater than a second preset matching value, if the highest matching value is greater than the second preset matching value, the electronic device may continuously determine whether the quality score of the target fingerprint image is greater than a preset score, if the quality score of the target fingerprint image is greater than the preset score, the electronic device may determine whether the second combination value is greater than the second preset combination value, and if the second combination value is greater than the second preset combination value, the electronic device may determine that the target fingerprint image satisfies a second preset condition. Therefore, the updating efficiency of the fingerprint template can be improved, and a foundation is provided for accurately and rapidly identifying the fingerprint subsequently.

In a possible implementation manner of the first aspect, the process of updating the fingerprint template library by the electronic device may specifically include: under the condition that the fingerprint verification image meets the first preset condition and the fingerprint restoration image meets the second preset condition, the electronic equipment updates the fingerprint verification image and the fingerprint restoration image into the fingerprint template library.

In this application, electronic equipment is with fingerprint verification image and fingerprint repair image update to fingerprint template storehouse in order to realize the dual-template and update, so, can realize the fingerprint identification under the different repair conditions, not only can promote template information's degree of accuracy, can increase template information's richness moreover.

In a possible implementation manner of the first aspect, the process of updating the fingerprint template library by the electronic device may specifically include: and under the condition that the number of the fingerprint templates in the fingerprint template library reaches the preset template number, deleting at least two fingerprint templates in the fingerprint template library by the electronic equipment. The electronic device then adds the fingerprint verification image and the fingerprint repair image to the fingerprint template library.

In the application, if the number of fingerprint templates reaches the preset number of templates, it is indicated that the fingerprint templates in the fingerprint template library are sufficient, the electronic device can delete at least two fingerprint templates in the fingerprint template library, take the fingerprint verification image and the fingerprint repair image as two new fingerprint templates, and add the two new fingerprint templates to the fingerprint template library at the same time to obtain a new fingerprint template library. Therefore, the precision of the fingerprint template can be improved on the basis of occupying no more storage space, and a basis is provided for subsequent successful fingerprint identification.

In a possible implementation manner of the first aspect, the method further includes: under the condition that the number of fingerprint templates in the fingerprint template library does not reach the preset template number and the phase difference number between the fingerprint template number and the preset template number is larger than 1, the electronic equipment adds the fingerprint verification image and the fingerprint repair image into the fingerprint template library.

In the application, if the number of the fingerprint templates does not reach the preset number of templates, it is indicated that the fingerprint templates in the fingerprint template library are insufficient, the electronic device can further judge whether the number of the phase differences between the number of the fingerprint templates and the preset number of the templates is larger than 1, if the number of the phase differences between the number of the fingerprint templates and the preset number of the templates is larger than 1, it is indicated that more template storage space still exists in the fingerprint template library, the electronic device can directly use the fingerprint verification image and the target fingerprint image as two new fingerprint templates, and the two new fingerprint templates are added into the fingerprint template library to obtain the new fingerprint template library. Therefore, on the basis of occupying no more storage space, more fingerprint templates are stored, and a basis is provided for subsequent successful fingerprint identification.

In a possible implementation manner of the first aspect, the method further includes: and under the condition that the number of the fingerprint templates in the fingerprint template library does not reach the preset template number and the phase difference number between the fingerprint template number and the preset template number is equal to 1, deleting at least one fingerprint template in the fingerprint template library by the electronic equipment. The electronic device then adds the fingerprint verification image and the fingerprint repair image to the fingerprint template library.

In the application, if the number of the differences between the number of the fingerprint templates and the number of the preset templates is equal to 1, it is indicated that only a small number of template storage spaces exist in the fingerprint template library, and the electronic device can delete at least one fingerprint template in the fingerprint template library. Then, the electronic device can take the fingerprint verification image and the target fingerprint image as two new fingerprint templates, and simultaneously add the two new fingerprint templates into the fingerprint template library to obtain a new fingerprint template library. Therefore, the precision of the fingerprint template can be improved on the basis of occupying no more storage space, and a basis is provided for subsequent successful fingerprint identification.

In a possible implementation manner of the first aspect, the process of acquiring the fingerprint repair image by the electronic device may specifically include: the electronic device captures a fingerprint verification image. And then, the electronic equipment judges whether a fingerprint template matched with the fingerprint verification image exists in the fingerprint template library, and repairs the fingerprint verification image according to the fingerprint repair model under the condition that the fingerprint template matched with the fingerprint verification image does not exist in the fingerprint template library, so as to obtain a fingerprint repair image.

In the application, if the fingerprint template matched with the fingerprint verification image does not exist in the fingerprint template library, the fact that the current user is likely to be a non-owner user is explained, in order to protect privacy of the user, the electronic equipment can repair the fingerprint verification image and further judge whether the electronic equipment can execute unlocking operation according to the fingerprint repair image, so that the success rate of fingerprint identification is improved, the situation that the current user cannot use the electronic equipment for the owner user is reduced, and the use experience of the user is improved.

In a possible implementation manner of the first aspect, the fingerprint repair model is obtained based on a fingerprint data set and generating an countermeasure network, wherein the fingerprint data set includes a first sub-fingerprint data set and a second sub-fingerprint data set, the first sub-fingerprint data set includes a plurality of fingerprint data in a normal state, the second sub-fingerprint data set includes a plurality of fingerprint data in an abnormal state, and a data number of the first sub-fingerprint data set is the same as a data number of the second sub-fingerprint data set.

In this application, because the quantity of first sub-fingerprint dataset and the quantity of second sub-fingerprint dataset are the same, and the quantity of the fingerprint data that is in dry state, the quantity of the fingerprint data that is in the low temperature state and the quantity of the fingerprint data that is in the moist state in the second sub-fingerprint dataset are the same, so, not only can reduce the condition emergence that reduces the model training precision because of positive and negative sample quantity unbalance, can also reduce the condition emergence that leads to the model training inefficiency because of negative sample (second sub-fingerprint dataset) quantity is too much, promote the training effect of model, and then promote the generalization ability of model, provide basis for follow-up generation fingerprint repair image.

In a possible implementation manner of the first aspect, the method further includes: in the case where there is no fingerprint template in the fingerprint template library that matches the fingerprint repair image, the electronic device does not perform an unlocking operation.

In the application, if the fingerprint template matched with the fingerprint repair image does not exist in the fingerprint template library, it is indicated that the current user is a non-owner user, and the electronic device may not execute the unlocking operation. Therefore, the method and the device can timely prevent the current user from carrying out corresponding operation on the electronic equipment, reduce the occurrence of the situation that the non-host user controls the electronic equipment, and avoid the loss of resources (such as property) of the user.

In a second aspect, the present application provides an electronic device comprising a display screen, a memory, and one or more processors; the display screen, the memory and the processor are coupled; the display screen is used for displaying a fingerprint acquisition area, and the memory is used for storing computer program codes, and the computer program codes comprise computer instructions; the computer instructions, when executed by the processor, cause the electronic device to perform the method as described above.

In a third aspect, the present application provides a computer readable storage medium comprising computer instructions which, when run on an electronic device, cause the electronic device to perform a method as described above.

In a fourth aspect, the present application provides a computer program product which, when run on an electronic device, causes the electronic device to perform the method as described above.

In a fifth aspect, there is provided a chip comprising: the device comprises an input interface, an output interface, a processor and a memory, wherein the input interface, the output interface, the processor and the memory are connected through an internal connection path, the processor is used for executing codes in the memory, and when the codes are executed, the processor is used for executing the method.

The advantages achieved by the electronic device according to the second aspect, the computer readable storage medium according to the third aspect, the computer program product according to the fourth aspect, and the chip according to the fifth aspect may refer to the advantages of the first aspect and any one of the possible design manners thereof, and are not described herein.

Drawings

Fig. 1 is a schematic diagram of a fingerprint collection area of a mobile phone according to an embodiment of the present application;

fig. 2 is a schematic diagram of a fingerprint collection area of a notebook computer according to an embodiment of the present application;

FIG. 3 is a schematic diagram of a normal fingerprint according to an embodiment of the present application;

fig. 4 is an interface schematic diagram of a fingerprint input process of an electronic device according to an embodiment of the present application;

FIG. 5 is a schematic diagram of a fingerprint verification process according to an embodiment of the present application;

fig. 6 is a schematic diagram of a finger in a low temperature state according to an embodiment of the present application;

fig. 7 is a schematic diagram of a finger in a wet state according to an embodiment of the present application;

fig. 8 is a schematic hardware structure of an electronic device according to an embodiment of the present application;

fig. 9 is a schematic software structure of an electronic device according to an embodiment of the present application;

fig. 10 is a flowchart of a fingerprint identification method in a fingerprint entry scenario provided in an embodiment of the present application;

fig. 11 is a flowchart of a fingerprint identification method in a fingerprint unlocking scenario provided in an embodiment of the present application;

fig. 12 is an interface schematic diagram of a mobile phone fingerprint recognition under a payment scenario provided in an embodiment of the present application;

fig. 13 is an interface schematic diagram of successful unlocking of a mobile phone according to an embodiment of the present application;

FIG. 14 is a schematic diagram of partitioning a fingerprint data set according to an embodiment of the present application;

Fig. 15 is a schematic diagram of a training generation network and a discrimination network according to an embodiment of the present application;

FIG. 16 is a schematic diagram of a training fingerprint repair model according to an embodiment of the present disclosure;

fig. 17 is a flowchart of a fingerprint identification method in a template updating scenario provided in an embodiment of the present application.

Detailed Description

The technical solutions in the embodiments of the present application will be described below with reference to the drawings in the embodiments of the present application. In the description of the present application, unless otherwise indicated, "and/or" in the present application is merely an association relationship describing an association object, and indicates that three relationships may exist, for example, a and/or B may indicate: there are three cases, a alone, a and B together, and B alone, wherein a, B may be singular or plural. Also, in the description of the present application, unless otherwise indicated, "a plurality" means two or more than two. "at least one of" or the like means any combination of these items, including any combination of single item(s) or plural items(s). For example, at least one (one) of a, b, or c may represent: a, b, c, a-b, a-c, b-c, or a-b-c, wherein a, b, c may be single or plural. In addition, in order to clearly describe the technical solutions of the embodiments of the present application, in the embodiments of the present application, the words "first", "second", and the like are used to distinguish the same item or similar items having substantially the same function and effect. It will be appreciated by those of skill in the art that the words "first," "second," and the like do not limit the amount and order of execution, and that the words "first," "second," and the like do not necessarily differ. Meanwhile, in the embodiments of the present application, words such as "exemplary" or "such as" are used to mean serving as examples, illustrations, or descriptions. Any embodiment or design described herein as "exemplary" or "for example" should not be construed as preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary" or "such as" is intended to present related concepts in a concrete fashion that may be readily understood.

The fingerprint identification method provided by the embodiment is applied to a fingerprint identification scene of electronic equipment, and generally, the fingerprint identification scene comprises a fingerprint input process and a fingerprint verification process (or referred to as a fingerprint unlocking process).

Under the scene of fingerprint input, the electronic equipment collects the fingerprint image of the user in the fingerprint collection area, and under the condition that the fingerprint image meets the fingerprint input requirement, the fingerprint image is input into a fingerprint template library of the electronic equipment.

For example, the fingerprint acquisition area of the electronic device may be in a designated area of the display screen of the electronic device. For example, referring to fig. 1, fig. 1 shows an example in which the fingerprint acquisition area is in the designated area 11 of the display screen when the electronic device is a mobile phone. Or, the fingerprint collection area may also be a designated area of the body of the electronic device, specifically, the designated area may be a side designated area, a back designated area, or other designated areas on the body of the electronic device, for example, the other designated areas on the body may be home keys of the mobile phone. For another example, referring to fig. 2, fig. 2 shows an example of the fingerprint acquisition area in the body designated area 12 when the electronic device is a notebook computer. It will be appreciated that for electronic devices that include a fingerprint sensor, the fingerprint acquisition area corresponds to the area in which the fingerprint sensor is located, i.e., the fingerprint acquisition area is the area in which the fingerprint sensor is located. The electronic equipment collects fingerprint images of the fingerprint collection area, and the size of the fingerprint images is consistent with that of the fingerprint collection area.

In some embodiments, in order to ensure the integrity of the acquired fingerprint image, the electronic device needs to acquire the fingerprint image from different angles of the finger of the user or different touch positions of the finger in the fingerprint acquisition area. For example, in the fingerprint input process, the threshold of the number of times of acquisition of the electronic device may be 20 times, 30 times, 50 times, etc., and the specific threshold of the number of times of acquisition is determined according to the actual electronic device. It will be appreciated that the number of acquisitions by the electronic device is different from the number of touches by the user, for example, the electronic device may perform multiple acquisitions of a fingerprint image over a period of time that the user touches once.

In one implementation, electronic devices typically employ an off-screen optical fingerprint recognition technique to capture the fingerprint image. The under-screen optical fingerprint identification technology is a new technology for completing a fingerprint identification unlocking process under a screen, and mainly utilizes penetration technologies such as ultrasonic waves, optics and the like to identify fingerprints. In particular, the off-screen optical fingerprinting technique typically uses organic light emitting semiconductors (organic electroluminescence display, OLED) as the light source for fingerprinting. The electronic device may then receive reflected light, wherein the reflected light is generated by reflecting light emitted by the OLED based on peaks (or ridges) and valleys (or grooves) of the finger print. The electronic device may then determine the fingerprint image based on the differences in the reflected light. Exemplary, as shown in fig. 3, fig. 3 is a schematic diagram of a finger print under normal conditions. The black lines 3A in the finger fingerprint are ridges of the finger for characterizing peaks of the finger fingerprint, which are ridges of the finger fingerprint, i.e. raised lines in the finger. The white lines 3B in the finger print are grooves of the finger for characterizing the valleys of the finger print, which are the concave portions between the lines of the finger, i.e. the lines of the depressions in the finger.

In the process of collecting fingerprint images for many times, the electronic equipment needs to judge fingerprint input conditions for the fingerprint images collected each time, and the fingerprint images meeting the fingerprint input conditions are stored in a fingerprint template library. Due to the device difference of the fingerprint sensor in the electronic device, the acquired original fingerprint image may have an original quality problem, and before the fingerprint input condition is determined, the electronic device may further perform image preprocessing on the acquired original fingerprint image, for example, performing image enhancement processing, image binarization processing and the like on the original fingerprint image. And then, the electronic equipment judges fingerprint input conditions of the preprocessed fingerprint image. The fingerprint input condition refers to a control condition on the image quality of the fingerprint image, for example, the fingerprint input condition includes at least one of that the image definition of the fingerprint image meets a definition threshold, that the image contrast of the fingerprint image meets a contrast threshold, that the effective fingerprint coverage area of the fingerprint image meets an area threshold, and the like. In a conventional scenario, an electronic device stores a fingerprint image in a fingerprint template library after determining that the fingerprint image satisfies a fingerprint entry condition. Here, the effective fingerprint coverage area refers to the area of the fingerprint image occupied by the fingerprint of the finger in the fingerprint image.

Under the scene of fingerprint input, a user can select fingerprint input through a menu interface to trigger the electronic equipment to enter a fingerprint input interface; alternatively, the user may trigger the electronic device to perform a fingerprint-entry action through voice control or other custom operations. Taking fig. 4 as an example for explanation, fig. 4 shows an example of fingerprint input based on a mobile phone display screen. Illustratively, the fingerprint-entry interface 300 includes a first prompt 301 and a "fingerprint" icon 302.

The "fingerprint" icon 302 is used to represent an area where a fingerprint image is collected, and a user may place a finger in the area where the "fingerprint" icon 302 is located to perform a touch operation to achieve the purpose of inputting a fingerprint. The first prompt 301 is used to prompt the user to enter a fingerprint. In some embodiments, at the interface position where the first prompting message 301 is located, the mobile phone may also display other prompting messages. For example, referring to fig. 4, fig. 4 shows a schematic diagram of the whole fingerprint input process of the user, when no fingerprint image is acquired, the mobile phone displays a first reminding message 301 for reminding the user to input the fingerprint in the interface 300, the first reminding message 301 is a sensing area in the finger pressing screen, the sensing area is removed after vibration is sensed, and the step is repeated; in the process of collecting the fingerprint image, the mobile phone can display second reminding information 303 for reminding the user to replace the finger position or angle and continuously record the fingerprint in the interface 300, wherein the second reminding information 303 can be "adjust the finger angle and record the edge of the finger"; when the actual collection number reaches the collection number threshold, that is, when the user completes the fingerprint input action, the mobile phone may further display third prompt information 304 in the interface 300 for reminding the user of completing the fingerprint input operation, for example, the third prompt information 304 may be "the current fingerprint is input". Then, in the case that the clicking operation of the user on the "complete" control 305 is detected, the mobile phone exits the current interface, that is, the newly-built fingerprint interface, so as to trigger the mobile phone to terminate the operation of collecting the fingerprint image currently.

After the recorded fingerprint image is contained in the fingerprint template library, when the electronic equipment collects a new fingerprint image under the condition of user authorization, whether the current user is a machine owner user or not can be judged according to the fingerprint template library and the newly collected fingerprint image, and the process can be called fingerprint verification. Specifically, in the fingerprint verification scenario, the electronic device may collect a fingerprint image of a user in a fingerprint collection area, match the collected fingerprint image with a fingerprint template in the fingerprint template library, and execute a fingerprint unlocking operation under the condition that the matching is determined to be successful. The fingerprint templates in the fingerprint template library refer to all fingerprint images recorded in the fingerprint recording process. It should be noted that the fingerprint collection area in the fingerprint unlocking scene is consistent with the fingerprint collection area in the fingerprint entering scene.

The fingerprint verification scene can comprise a scene of unlocking a screen locking interface, unlocking an application and the like of the electronic equipment. The screen locking interface unlocking means that the electronic equipment is positioned on the screen locking interface, and the electronic equipment enters the system main interface of the electronic equipment by collecting fingerprint images of users under the condition that the fingerprint images are successfully matched. The application unlocking comprises the scenes of unlocking the encryption application, payment unlocking and the like, for example, under the condition that the unlocking operation of the encryption application is triggered, the electronic equipment enters an unlocking main interface of the application through collecting fingerprint images of a user under the condition that the fingerprint images are successfully matched. For another example, in the case of triggering payment unlocking, the electronic device performs a payment operation by collecting a fingerprint image of a user, in the case of successful fingerprint image matching.

In the process of fingerprint verification, similar to the fingerprint input process, the electronic device also performs image preprocessing on the acquired fingerprint image. Then, the electronic equipment matches the preprocessed fingerprint image with fingerprint templates in a fingerprint template library, if the fingerprint templates matched with the fingerprint images exist in the fingerprint template library, the acquired fingerprint images are determined to be fingerprint images of input fingerprints, and the electronic equipment can execute unlocking operation; if no fingerprint template matched with the fingerprint image exists in the fingerprint template library, that is, the fingerprint image is not matched with all the fingerprint templates, it is determined that the acquired fingerprint image is not the fingerprint image of the input fingerprint, and the electronic device can not respond to the unlocking operation.

In one implementation manner, referring to fig. 5, specifically, after the electronic device collects the fingerprint image, the electronic device may determine whether a fingerprint template matching the fingerprint image exists in the fingerprint template library, and if the fingerprint template matching the fingerprint image does not exist in the fingerprint template library, it indicates that the current user is a non-host user, and correspondingly, the electronic device does not perform the unlocking operation, so as to protect the privacy of the user. Wherein the fingerprint template library comprises a plurality of fingerprint templates.

If a fingerprint template matched with the fingerprint image exists in the fingerprint template library, the current user is a host user, the electronic equipment can execute unlocking operation, and whether the fingerprint image meets the preset condition is judged. The preset condition is used for evaluating whether the fingerprint image can be updated into the fingerprint template library, the preset condition is determined based on a matching value of the fingerprint image and a target fingerprint template and/or a quality fraction of the fingerprint image, and the target fingerprint template is a fingerprint template matched with the fingerprint image in the fingerprint template library. And then, under the condition that the fingerprint image meets the preset condition, updating the fingerprint templates in the fingerprint template library to obtain a new fingerprint template library. Or, in case the fingerprint image does not satisfy the preset condition, the electronic device does not perform the template updating operation.

In some embodiments, the fingerprint verification process described above can implement a fingerprint identification function, but if the fingerprint is in a wet, low-temperature or dry weather environment, that is, the user's finger is in an abnormal condition (such as a dry finger, a low-temperature finger, a wet finger, etc.), the electronic device may not accurately collect the fingerprint of the user, that is, the quality of the fingerprint image collected by the electronic device is low, so that the fingerprint identification rate is greatly reduced, and the use experience of the user is further affected. It can be understood that under the condition that the finger is in a normal state, the difference between the reflected light corresponding to the wave peak and the reflected light corresponding to the wave trough in the finger of the user is obvious, namely, the wave peak is black in the fingerprint image (shown as 3A in FIG. 3), the wave trough is white in the fingerprint image (shown as 3B in FIG. 3), and the electronic equipment can still meet the use requirement of the user by adopting the fingerprint verification process, so that the use experience of the user is ensured.

Wherein, the dry finger refers to a finger in a dry state. It can be appreciated that, under the condition that the finger is in a dry state, the line of the finger can be shallow, so that the difference between the reflected light corresponding to the wave peak and the reflected light corresponding to the wave trough in the finger of the user is small, and further the electronic device may not collect a clear fingerprint image, that is, the difference between the collected fingerprint image and the pre-stored fingerprint image is large, and finally the success rate of fingerprint identification is reduced.

The low-temperature finger refers to a finger in a low-temperature state. It can be appreciated that under the condition that the finger is in a low temperature state, the hand becomes drier, and the lines of the finger become shallower, so that the difference between the reflected light corresponding to the wave peak and the reflected light corresponding to the wave trough in the finger of the user is smaller (as shown in fig. 6), and further the electronic device may not collect a clear fingerprint image, that is, the difference between the collected fingerprint image and the pre-stored fingerprint image is larger, which finally results in a reduced success rate of fingerprint identification.

The wet finger refers to a finger in a wet state. It can be appreciated that under the condition that the finger is in a wet state, a water film layer is formed on the fingerprint surface of the finger, and the water film layer may fill the concave portion between the plain lines, that is, fill the valley portion in the finger, so as to affect the refractive index of the OLED at the valley position, so that the refractive light difference between the peak and the valley is not large (as shown in fig. 7), and further the electronic device may not be able to collect a clear fingerprint image, that is, the difference between the collected fingerprint image and the pre-stored fingerprint image is large, which finally results in a reduced success rate of fingerprint identification.

In order to improve the success rate of fingerprint identification, the embodiment of the application provides a fingerprint identification method. In the method, in response to touch operation of a user on a fingerprint acquisition area of electronic equipment, the electronic equipment acquires a fingerprint restoration image, wherein the fingerprint restoration image is an image generated after a fingerprint verification image acquired by the electronic equipment is restored. And then, the electronic equipment judges whether a fingerprint template matched with the fingerprint restoration image exists in a fingerprint template library, wherein the fingerprint template library comprises at least one fingerprint template. Then, in the case that a fingerprint template matched with the fingerprint repair image exists in the fingerprint template library, the electronic device updates the fingerprint verification image and/or the fingerprint repair image into the fingerprint template library.

The dual-template updating refers to a process of taking a fingerprint verification image and a fingerprint restoration image as two new fingerprint templates and updating the two new fingerprint templates into a fingerprint template library. The updating of the fingerprint template refers to adding or replacing the fingerprint image to the fingerprint template library. How the template updating is performed will be described in detail later.

It can be understood that the electronic device updates the fingerprint image (or referred to as fingerprint verification image) before repairing into the fingerprint template library, so that the fingerprint recognition efficiency of the electronic device can be improved, that is, the electronic device can acquire a similar fingerprint verification image next time without repairing through a fingerprint repairing model, and the fingerprint recognition can be realized. In addition, the electronic equipment updates the repaired fingerprint image (or referred to as fingerprint repair image) to the fingerprint template library, so that the image quality of each fingerprint template in the fingerprint template library can reach the preset quality requirement, further, the fingerprint identification precision can be improved, the occurrence of the situation of error identification or missing identification of the electronic equipment is reduced, and the use experience of a user is improved.

For example, the electronic device in the embodiments of the present application may be a mobile phone, a tablet computer, a notebook computer, an ultra-mobile personal computer (ultra-mobile personal computer, UMPC), a handheld computer, a netbook, a personal digital assistant (personal digital assistant, PDA), a wearable device (such as a smart watch, a smart glasses or a smart helmet), a virtual reality device, a smart home device, an on-vehicle computer, an access control device, or an electronic device including a fingerprint identification module, and the specific form of the electronic device is not limited in the following embodiments.

Taking the example that the electronic device is a mobile phone. Fig. 8 shows a schematic structural diagram of the electronic device 200.

By way of example, fig. 8 shows a schematic structural diagram of an electronic device 200. As shown in fig. 8, the electronic device 200 may include a processor 210, an external memory interface 220, an internal memory 221, a universal serial bus (universal serial bus, USB) interface 230, a charge management module 211, a power management module 212, a battery 213, an antenna 1, an antenna 2, a mobile communication module 240, a wireless communication module 250, an audio module 270, a sensor module 280, keys 290, a motor 291, an indicator 292, cameras 1-N293, a display 294, and subscriber identity module (subscriber identification module, SIM) card interfaces 1-N295, etc.

It should be understood that the structure illustrated in the embodiments of the present invention does not constitute a specific limitation on the electronic device 200. In other embodiments of the present application, electronic device 200 may include more or fewer components than shown, or certain components may be combined, or certain components may be split, or different arrangements of components. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

Processor 210 may include one or more processing units such as, for example: the processor 210 may include an application processor (application processor, AP), a modem processor, a graphics processor (graphics processing unit, GPU), an image signal processor (image signal processor, ISP), a controller, a memory, a video codec, a digital signal processor (digital signal processor, DSP), a baseband processor, and/or a neural network processor (neural-network processing unit, NPU), etc. Wherein the different processing units may be separate devices or may be integrated in one or more processors.

The controller may be a neural hub and a command center of the electronic device 200, among others. The controller can generate operation control signals according to the instruction operation codes and the time sequence signals to finish the control of instruction fetching and instruction execution.

A memory may also be provided in the processor 210 for storing instructions and data. In some embodiments, the memory in the processor 210 is a cache memory. The memory may hold instructions or data that the processor 210 has just used or recycled. If the processor 210 needs to reuse the instruction or data, it may be called directly from the memory. Repeated accesses are avoided and the latency of the processor 210 is reduced, thereby improving the efficiency of the system.

In some embodiments, processor 210 may include one or more interfaces. The interfaces may include an integrated circuit (inter-integrated circuit, I2C) interface, an integrated circuit built-in audio (inter-integrated circuit sound, I2S) interface, a pulse code modulation (pulse code modulation, PCM) interface, a universal asynchronous receiver transmitter (universal asynchronous receiver/transmitter, UART) interface, a mobile industry processor interface (mobile industry processor interface, MIPI), a general-purpose input/output (GPIO) interface, a subscriber identity module (subscriber identity module, SIM) interface, and/or a universal serial bus (universal serial bus, USB) interface, among others.

It should be understood that the connection relationship between the modules illustrated in the embodiment of the present invention is only illustrative, and does not limit the structure of the electronic device 200. In other embodiments of the present application, the electronic device 200 may also use different interfacing manners, or a combination of multiple interfacing manners, as in the above embodiments.

The charge management module 211 is configured to receive a charge input from a charger. The charging management module 211 may also supply power to the electronic device through the power management module 212 while charging the battery 213.

The wireless communication function of the electronic device 200 can be implemented by the antenna 1, the antenna 2, the mobile communication module 240, the wireless communication module 250, a modem processor, a baseband processor, and the like.

The antennas 1 and 2 are used for transmitting and receiving electromagnetic wave signals. Each antenna in the electronic device 200 may be used to cover a single or multiple communication bands. Different antennas may also be multiplexed to improve the utilization of the antennas. For example: the antenna 1 may be multiplexed into a diversity antenna of a wireless local area network. In other embodiments, the antenna may be used in conjunction with a tuning switch.

The mobile communication module 240 may provide a solution for wireless communication including 2G/3G/4G/5G, etc., applied on the electronic device 200. The modem processor may include a modulator and a demodulator.

The wireless communication module 250 may provide solutions for wireless communication including wireless local area network (wireless local area networks, WLAN) (e.g., wireless fidelity (wireless fidelity, wi-Fi) network), bluetooth (BT), global navigation satellite system (global navigation satellite system, GNSS), frequency modulation (frequency modulation, FM), near field wireless communication technology (near field communication, NFC), infrared technology (IR), etc., as applied on the electronic device 200.

The electronic device 200 implements display functions through a GPU, a display screen 294, an application processor, and the like. The GPU is a microprocessor for image processing, and is connected to the display screen 294 and the application processor. The GPU is used to perform mathematical and geometric calculations for graphics rendering. Processor 210 may include one or more GPUs that execute program instructions to generate or change display information.

A display screen (or screen) 294 is used to display images, videos, and the like. In some embodiments, in the context of fingerprint entry, display 294 may display a prompt to prompt the user to begin entering a fingerprint, or to prompt the user to change angles to continue entering a fingerprint, or to prompt the user to complete fingerprint entry. In the scenario of fingerprint authentication, the display 294 may also display a prompt for alerting the user to the failure of authentication. In the scene of fingerprint input or fingerprint verification, if the fingerprint is in a dry state, a wet state or a low-temperature state, the display screen can also display prompt information (such as the current fingerprint is in a wet state, verification is performed after the fingerprint is wiped), and the like, which are used for reminding a user of the reason of failure in verification.

Wherein the display 294 includes a display panel. The display panel may employ a liquid crystal display (liquid crystal display, LCD), an organic light-emitting diode (OLED), an active-matrix organic light-emitting diode (AMOLED) or an active-matrix organic light-emitting diode (matrix organic light emitting diode), a flexible light-emitting diode (flex), a mini, a Micro led, a Micro-OLED, a quantum dot light-emitting diode (quantum dot light emitting diodes, QLED), or the like. In some embodiments, the electronic device 200 may include 1 or N display screens 294, N being a positive integer greater than 1.

The electronic device 200 may implement a photographing function through an ISP, a camera 293, a video codec, a GPU, a display 294, an application processor, and the like.

The ISP is used to process the data fed back by the camera 293. For example, when an electronic device photographs, the shutter is opened, light is transmitted to a camera photosensitive element (or referred to as an image sensor) through the lens, an optical signal is converted into an electrical signal, and the camera photosensitive element transmits the electrical signal to an ISP for processing, so that the electrical signal is converted into an image visible to the naked eye. ISP can also perform algorithm optimization on noise and brightness of the image. The ISP can also optimize parameters such as exposure, color temperature and the like of a shooting scene. In some embodiments, the ISP may be provided in the camera 293. In some embodiments, camera 293 includes a shutter. The shutter is a device in the camera for controlling the time at which light irradiates the photosensitive element.

The camera 293 is used to capture still images or video. The object generates an optical image through the lens and projects the optical image onto the photosensitive element. The photosensitive element may be a charge coupled device (charge coupled device, CCD) or a Complementary Metal Oxide Semiconductor (CMOS) phototransistor. The photosensitive element converts the optical signal into an electrical signal, which is then transferred to the ISP to be converted into a digital image signal. The ISP outputs the digital image signal to the DSP for processing. The DSP converts the digital image signal into an image signal in a standard RGB, YUV, or the like format. In some embodiments, the electronic device 200 may include 1 or N cameras 293, N being a positive integer greater than 1.

The digital signal processor is used for processing digital signals, and can process other digital signals besides digital image signals. For example, when the electronic device 200 is selecting a frequency bin, the digital signal processor is used to fourier transform the frequency bin energy, or the like.

The NPU is a neural-network (NN) computing processor, and can rapidly process input information by referencing a biological neural network structure, for example, referencing a transmission mode between human brain neurons, and can also continuously perform self-learning. Applications such as intelligent awareness of the electronic device 600 may be implemented through the NPU, for example: image recognition, face recognition, speech recognition, text understanding, etc. In this embodiment, the NPU may be used to perform fingerprint image recognition, fingerprint image matching, and the like.

In some embodiments, the NPU may refer to the target recognition model, and process the input information to obtain the user identity.

The external memory interface 220 may be used to connect an external memory card, such as a Micro SD card, to enable expansion of the memory capabilities of the electronic device 200.

Internal memory 221 may be used to store computer executable program code that includes instructions. The processor 210 executes various functional applications of the electronic device 200 and data processing by executing instructions stored in the internal memory 221. The internal memory 221 may include a storage program area and a storage data area. The storage program area may store an application program (such as a sound playing function, an image playing function, etc.) required for at least one function of the operating system, etc. The storage data area may store data created during use of the electronic device 200 (e.g., audio data, phonebook, etc.), and so on. In addition, the internal memory 221 may include a high-speed random access memory, and may further include a nonvolatile memory such as at least one magnetic disk storage device, a flash memory device, a universal flash memory (universal flash storage, UFS), and the like.

The electronic device 200 may implement audio functions through an audio module 270, an application processor, and the like. Such as music playing, recording, etc. The audio module 270 may include, among other things, a speaker, a receiver, a microphone, and a headset interface.

Keys 290 include a power on key, a volume key, etc. The indicator 292 may be an indicator light.

The sensor module 280 may include a pressure sensor, a gyroscope sensor, a barometric sensor, a magnetic sensor, an acceleration sensor, a distance sensor, a proximity sensor, a fingerprint sensor, a temperature sensor, a touch sensor, an ambient light sensor, a bone conduction sensor, and the like.

The fingerprint sensor is used for collecting fingerprints. The electronic device 200 can utilize the collected fingerprint characteristics to realize fingerprint unlocking, access an application lock, fingerprint photographing, fingerprint incoming call answering and the like. In some embodiments, the fingerprint sensor transmits the acquired fingerprint image to a processor, which performs a fingerprint entry or fingerprint verification operation based on the fingerprint image. Alternatively, the fingerprint sensor may be an optical fingerprint sensor, a capacitive fingerprint sensor, an ultrasonic fingerprint sensor, or the like. In this embodiment, the fingerprint sensor may be disposed under a screen of a display screen of the electronic device or disposed at a designated position of a body of the electronic device, where the position where the fingerprint sensor is disposed corresponds to the fingerprint collection area. For example, referring to fig. 1 again, the fingerprint sensor is disposed under the display screen of the mobile phone, and the corresponding fingerprint acquisition area is area 11. For another example, referring again to fig. 2, the fingerprint sensor is disposed at a designated position of the body of the notebook computer, and the corresponding fingerprint acquisition area is area 12. The fingerprint sensor may also be provided at a side designated position, a back designated position, or the like of the electronic device. The setting position of the fingerprint sensor may be determined according to the unlocking habit of the user using the electronic device, which is not limited in this embodiment.

Touch sensors, also known as "touch panels". May be provided on the display 294. For detecting a touch operation acting on or near it. The detected touch operation may be communicated to an application processor to determine the touch event type and provide a corresponding visual output through the display 294.

The pressure sensor is used for sensing a pressure signal and can convert the pressure signal into an electric signal. In some embodiments, a pressure sensor may be provided at the display 294. Pressure sensors are of many kinds, such as resistive pressure sensors, inductive pressure sensors, capacitive pressure sensors, etc. The capacitive pressure sensor may be a capacitive pressure sensor comprising at least two parallel plates with conductive material. When a force is applied to the pressure sensor, the capacitance between the electrodes changes. The electronic device 200 determines the strength of the pressure from the change in capacitance. When a touch operation is applied to the display screen 294, the electronic apparatus 200 detects the touch operation intensity according to the pressure sensor. The electronic device 200 may also calculate the location of the touch based on the detection signal of the pressure sensor. In some embodiments, touch operations that act on the same touch location, but at different touch operation strengths, may correspond to different operation instructions. For example: and executing an instruction for checking the short message when the touch operation with the touch operation intensity smaller than the first pressure threshold acts on the short message application icon. And executing an instruction for newly creating the short message when the touch operation with the touch operation intensity being greater than or equal to the first pressure threshold acts on the short message application icon.

The proximity light sensor may include, for example, a Light Emitting Diode (LED) and a light detector, such as a photodiode. The light emitting diode may be an infrared light emitting diode. Infrared light is emitted outwards by the light emitting diode. A photodiode is used to detect infrared reflected light from nearby objects. When sufficient reflected light is detected, it may be determined that an object is in the vicinity of the electronic device 200. When insufficient reflected light is detected, it may be determined that there is no object in the vicinity of the electronic device 200. The electronic device 200 can detect that the user holds the electronic device 200 close to the ear to talk by using the proximity light sensor, so as to automatically extinguish the screen to achieve the purpose of saving electricity. The proximity light sensor can also be used in a holster mode, and a pocket mode can be used for automatically unlocking and locking a screen.

The software system of the electronic device 200 may employ a layered architecture, an event driven architecture, a microkernel architecture, a microservice architecture, or a cloud architecture. In the embodiment of the invention, taking an Android system with a layered architecture as an example, a software structure of the electronic device 200 is illustrated.

Fig. 9 is a software configuration block diagram of the electronic device 200 according to the embodiment of the present invention. Embodiments of the present application will be discussed based on the following technical architecture. It should be noted that, for convenience of description of logic, only the service logic relationship is described by using a schematic block diagram, and the specific location of the technical architecture where each service is located is not strictly expressed. In addition, the naming of each module in the software architecture diagram is taken as an exemplary example, the naming of each module in the software architecture diagram is not limited in the embodiment of the present application, and in actual implementation, the specific naming of the module may be determined according to actual requirements.

The layered architecture divides the software layer into several layers, each with distinct roles and branches. The layers communicate with each other through a software interface. In some embodiments, the Android system includes four layers, from top to bottom, an application layer (applications), an application framework layer (application framework), a hardware abstraction layer (hardware abstraction layer, HAL), and a kernel layer (kernel), respectively.

The application layer may include a series of application packages, among other things. For example, the application package may include applications such as telephony (i.e., a "telephony" application in embodiments of the present application), short messages, video, navigation, and the like.

The application framework layer provides an application programming interface (application programming interface, API) and programming framework for application programs of the application layer. The application framework layer includes a number of predefined functions. As shown in fig. 9, the application framework layer may include a template update module, a fingerprint template library, a fingerprint identification module, and a fingerprint repair module.

The template updating module is used for updating the fingerprint templates in the fingerprint template library. Specifically, the template updating module may use the target fingerprint image satisfying the preset condition as a new fingerprint template, and add the new fingerprint template to the fingerprint template library to obtain a new fingerprint template library. The target fingerprint image is a fingerprint image capable of enabling the electronic equipment to be successfully unlocked.

The fingerprint template library is used for storing a plurality of fingerprint templates corresponding to the electronic device 200, that is, the fingerprint template library includes a plurality of fingerprint templates, and at least one fingerprint image is included in the fingerprint templates.

The fingerprint identification module is used for carrying out operations such as image preprocessing, image judgment, image matching, fingerprint template library updating and the like on the fingerprint image. After receiving the fingerprint image, the fingerprint identification module performs preprocessing such as image enhancement, image binarization and the like on the fingerprint image. In a fingerprint input scene, the fingerprint identification module judges whether the preprocessed fingerprint image meets fingerprint input conditions or not, and the template updating module inputs the fingerprint image into a fingerprint template library under the condition that the fingerprint image is confirmed to meet the fingerprint input conditions. Under the fingerprint verification scene, the fingerprint identification module performs image matching on the preprocessed fingerprint image, matches the fingerprint image with a fingerprint template in the fingerprint template library, and performs fingerprint unlocking operation under the condition of successful matching. Under the scene of updating the fingerprint template, the template updating module updates the fingerprint image conforming to the template updating condition into the fingerprint template library.

The fingerprint restoration module is used for restoring the fingerprint image acquired by the electronic device 200 to obtain a fingerprint restoration image. And then, the fingerprint identification module matches the fingerprint restoration image with the fingerprint templates in the fingerprint template library, and under the condition of successful matching, fingerprint unlocking operation is executed. Under the scene of updating the fingerprint template, the template updating module updates the fingerprint repair image conforming to the template updating condition into the fingerprint template library.

The hardware abstraction layer is the encapsulation of the Linux kernel driver, provides an interface upwards, hides the hardware interface details of a specific platform, and provides a virtual hardware platform for an operating system. In the embodiment of the application, the hardware abstraction layer comprises a fingerprint HAL. In other embodiments, the hardware abstraction layer may also include modules such as camera HAL, audio HAL, GPS HAL, wi-Fi HAL, and the like.

The kernel layer is a layer between hardware and software. The kernel layer includes a fingerprint driver. In some embodiments, the kernel layer may also include display drivers, camera drivers, audio drivers, sensor drivers, and the like.

The software architecture of the electronic device 200 described above may also include a system library that includes a plurality of functional modules, for example. For example: surface manager (surface manager), media library (media library), three-dimensional graphics processing library (e.g., openGL ES), 2D graphics engine (e.g., SGL), etc. The surface manager is used for managing the display subsystem and providing fusion of 2D and 3D layers for a plurality of application programs. Media libraries support a variety of commonly used audio, video format playback and recording, still image files, and the like. The media library may support a variety of audio and video encoding formats, such as MPEG4, h.264, MP3, AAC, AMR, JPG, PNG, etc. The three-dimensional graphic processing library is used for realizing three-dimensional graphic drawing, image rendering, synthesis, layer processing and the like. The 2D graphics engine is a drawing engine for 2D drawing.

The hardware layer provides various hardware devices, such as the hardware devices involved in embodiments of the present application include fingerprint sensors. The fingerprint sensor is used for collecting fingerprint images of the fingers of the user.

It will be appreciated that the layers and components contained in the layers in the structure shown in fig. 9 do not constitute a specific limitation on the electronic device 200, i.e., the mobile phone. In other embodiments of the present application, the structure may include more or fewer layers than shown, and more or fewer components may be included in each layer, as the present application is not limited.

In some embodiments, the electronic device triggers the fingerprint sensor to capture a fingerprint verification image in response to a user's touch operation on a fingerprint capture area in the new fingerprint entry interface. The fingerprint sensor may then send a fingerprint verification image to the fingerprint recognition module to trigger the fingerprint recognition module to fingerprint the fingerprint verification image. And then, the fingerprint identification module can be matched with the fingerprint templates in the fingerprint template library according to the identified fingerprint data, and under the condition of successful matching, fingerprint unlocking operation is executed.

In the event of a failure of the match, the fingerprint identification module may send a fingerprint verification image to the fingerprint repair module. And then, the fingerprint restoration module can restore the received fingerprint verification image to obtain a fingerprint restoration image. The fingerprint repair module may then send the fingerprint repair image to the fingerprint identification module. And then, the fingerprint identification module can match the fingerprint repair image with the fingerprint templates in the fingerprint template library, and under the condition of successful matching, fingerprint unlocking operation is executed.

In the process of executing the fingerprint unlocking operation, the template updating module can judge that the fingerprint verification image and the fingerprint restoration image which meet the preset conditions are respectively used as a new fingerprint template, and the two new fingerprint templates are added into the fingerprint template library to obtain a new fingerprint template library.

Based on the electronic device described in the above exemplary embodiments, the embodiment of the application provides a fingerprint identification method. The method can be applied to any fingerprint identification scene, such as a fingerprint input scene, a fingerprint unlocking scene, a template updating scene and the like. The method of the embodiment of the application is described below by taking electronic equipment as a mobile phone and an application scene as a fingerprint input scene as an example. Specifically, as shown in fig. 10, the fingerprint identification method may include S1001 to S1004.

S1001, the mobile phone displays a new fingerprint input interface.

The new fingerprint input interface is used for inputting new fingerprints. Illustratively, as shown in FIG. 4, the interface 300 is a new fingerprint-entry interface that includes a first reminder 301 and a "fingerprint" icon 302. The area corresponding to the "fingerprint" icon 302 is the fingerprint collection area. The first reminding information 301 reminds the user of touching the "fingerprint" icon 302 to enable the mobile phone to perform fingerprint input operation.

In one example, the user may trigger the handset to display a new fingerprint-entry interface by clicking on a "new fingerprint-entry" option in the menu interface. In another example, the user may also trigger the cell phone to display a new fingerprint entry interface by voice entering a "new fingerprint entry" manner.

It should be noted that, the personal information (such as fingerprint information) used in the technical solution of the present application is limited to information that is agreed with by a person alone, including, but not limited to, notifying and reminding the user to read the relevant user protocol (notification) and signing the protocol (authorization) including the information about the authorized relevant user before the user uses the function.

S1002, responding to touch operation of a user on a fingerprint acquisition area in a new fingerprint input interface, and acquiring a fingerprint input image by the mobile phone.

In some embodiments, after the mobile phone displays the new fingerprint input interface, if the finger is detected to contact the fingerprint acquisition area, the mobile phone can acquire the fingerprint input by the user to obtain a fingerprint input image, which indicates that the user is inputting a new fingerprint.

For example, referring again to fig. 4, at various stages of the fingerprint-entry process, the new fingerprint-entry interface may include a first reminder 301, a second reminder 303, and a third reminder 304. For example, when a fingerprint is not entered, the first reminder 301 may remind the user to press at the "fingerprint" icon 302 to cause the mobile phone to perform a fingerprint entry operation. For another example, in the process of inputting a fingerprint, the second reminding information 303 may remind the user to adjust the finger position to continuously press the "fingerprint" icon 302 for fingerprint input. For another example, the third reminder 304 may remind the user to complete the fingerprint entry when the fingerprint entry is completed.

Specifically, under the condition that the contact of the finger with the fingerprint collecting area is detected, the mobile phone can collect the fingerprint of the contact part of the finger of the user and the fingerprint collecting area through the fingerprint sensor, and a corresponding fingerprint input image is generated. Optionally, after the mobile phone collects the fingerprint input image, the mobile phone can preprocess the fingerprint input image to obtain the preprocessed fingerprint input image, so as to improve the image original quality problems such as image blurring caused by the fingerprint sensor. Illustratively, the preprocessing may include at least one of image enhancement processing, image binarization processing, and the like.

S1003, the mobile phone judges whether the acquisition times of the fingerprint input images reach the preset acquisition times.

Specifically, after the mobile phone collects the fingerprint input image, the mobile phone can record the collection times of the fingerprint input image, judge whether the collection times reach the preset collection times, if the collection times reach the preset collection times, it is indicated that the mobile phone has collected the complete fingerprint, and the mobile phone can execute S1004. If the collection times do not reach the preset collection times, the mobile phone indicates that the mobile phone does not collect the complete finger fingerprint currently, that is, the fingerprint area still exists, the mobile phone can return to execute S1002 to continue collecting the fingerprint input image until the collection times reach the preset collection times, so that the integrity of the input fingerprint can be ensured.

In the fingerprint input process of the embodiment, in order to input the integrity of the fingerprint, the finger fingerprints of the user need to be acquired for many times from different angles, the acquisition times can be recorded and updated when the fingerprint input image is acquired once, and the fingerprint input image is stored in a designated permanent storage space. Wherein the storage space refers to a permanent secure storage space, such as a flash memory of a mobile phone.

In some embodiments, the space where the mobile phone can store data further includes a temporary storage space, for example, a secure memory of the mobile phone, and in a scenario where fingerprint unlocking or fingerprint support is performed, the mobile phone can load the fingerprint templates in the fingerprint template library into the secure memory for fingerprint matching. The secure memory may be a register memory or a mobile phone cache.

In one implementation, after determining that the number of collection times of the fingerprint input image does not reach the preset number of collection times, the mobile phone may repeatedly perform the operation of collecting the fingerprint input image, and at the same time, the mobile phone may output, in the new fingerprint input interface, prompt information (such as the second prompt information 303 in fig. 4) for reminding the user to adjust the angle or the position of the finger to continue fingerprint input until the number of collection times reaches the preset number of collection times, so as to obtain a plurality of fingerprint input images meeting the fingerprint input condition in the cache. The preset collection times may be determined according to practical situations, for example, 30 times, 60 times, and the like. It should be noted that, in a period of time that the user touches once, the mobile phone can control the fingerprint sensor to collect fingerprint input images for a plurality of times, where the collection times of the fingerprint sensor are different from the contact times of the user in the fingerprint collection area.

S1004, the mobile phone takes the collected fingerprint input image as a new fingerprint template, and inputs the new fingerprint template into a fingerprint template library.

Specifically, after the acquisition times reach the preset acquisition times, the mobile phone can take the acquired fingerprint input image as a new fingerprint template and input the new fingerprint template into a fingerprint template library, so that a basis can be provided for subsequent fingerprint verification. It will be appreciated that the library of fingerprint templates may comprise less than or equal to the number of preset templates, that is, the library of fingerprint templates is at most capable of storing a preset number of templates of fingerprint templates, and each fingerprint template comprises a corresponding number of fingerprint entry images. The number of the preset templates may be set according to actual situations, for example, the number of the preset templates may be 5, 10, etc., which is not limited specifically.

In some embodiments, the mobile phone can record the collected fingerprint input images with preset collection times as a new fingerprint template into a fingerprint template library; or the mobile phone can select a preset number of fingerprint input images from the fingerprint input images with preset collection times, and input the preset number of fingerprint input images into a fingerprint template library as a new fingerprint template; or the mobile phone can select all fingerprint input images meeting the requirement of a preset template from the fingerprint input images of the preset acquisition times, and input the all fingerprint input images into a fingerprint template library as a new fingerprint template. The preset template requirement may include at least one of an image quality of the fingerprint-entry image meeting a preset quality requirement and a fingerprint integrity of the fingerprint-entry image being greater than a preset integrity.

For example, as shown in fig. 4, after the third alert information 304 and the "finish" control 305 are displayed, the mobile phone may input the currently input fingerprint into the fingerprint template in response to the clicking operation of the user on the "finish" control 305, so as to implement the storage operation of the finger fingerprint.

In one implementation, after determining that the collection times reach the preset collection times, the mobile phone may construct a fingerprint vector according to the collected fingerprint input image, and input the fingerprint vector as a new fingerprint template into the fingerprint template library. That is, the new fingerprint template may include a plurality of fingerprint input images, or may include a fingerprint vector, and the specific template input form is not limited.

The method of the embodiment of the application will be described by taking the electronic device as a mobile phone and the application scene as a fingerprint unlocking scene as an example. Specifically, on the premise that at least one fingerprint template exists in the fingerprint template library, the mobile phone can judge whether the mobile phone can execute fingerprint unlocking operation or not based on the fingerprint template in the fingerprint template library and the fingerprint verification image acquired by the mobile phone. For example, as shown in fig. 11, the fingerprint identification method may include S1101 to S1106.

S1101, responding to touch operation of a user on the fingerprint acquisition area, and acquiring a fingerprint verification image by the mobile phone.

Specifically, the user can input the finger fingerprint by touching the fingerprint acquisition area. And then, the mobile phone can collect fingerprint verification images according to the contact operation of the user.

In some scenarios, if it is detected that the user's finger touches the fingerprint acquisition area while the mobile phone is in the lock screen or sleep mode, the mobile phone may acquire the fingerprint authentication image. And then, the mobile phone can verify the identity of the user according to the fingerprint verification image so as to judge whether the mobile phone can execute unlocking operation. For example, referring to fig. 1 again, the fingerprint collection area may be an area 11, and if the mobile phone detects that the user's finger touches the area 11, the mobile phone may collect a corresponding fingerprint verification image according to the touch operation, so as to further determine whether the mobile phone can perform the unlocking operation.

In other scenarios, if it is detected that the user's finger touches the fingerprint acquisition area, the mobile phone may acquire the fingerprint authentication image while the mobile phone is in the payment mode. And then, the mobile phone can verify the identity of the user according to the fingerprint verification image so as to judge whether the mobile phone can execute payment operation or not. For example, referring to fig. 12, the interface (a) is an interface to be paid, the fingerprint collection area may be an area 121 in the interface (a), and if the mobile phone detects that the user's finger touches the area 121, the mobile phone may collect a corresponding fingerprint verification image according to the touch operation, so as to further determine whether the mobile phone can perform the payment operation.

S1102, the mobile phone judges whether a fingerprint template matched with the fingerprint verification image exists in the fingerprint template library.

In some embodiments, after the fingerprint verification image is collected, the mobile phone may determine whether a fingerprint template matching the fingerprint verification image exists in the fingerprint template library, and if the fingerprint template matching the fingerprint verification image exists in the fingerprint template library, it indicates that the current user is a host user, and the mobile phone may execute S1103. If there is no fingerprint template matching the fingerprint verification image in the fingerprint template library, which indicates that the current user may be a non-owner user, the mobile phone may execute S1104 to further determine whether the mobile phone may execute the unlocking operation, so that the privacy of the user may be protected.

In one implementation, after the mobile phone collects the fingerprint verification image, the mobile phone may first perform preprocessing on the fingerprint verification image to obtain a processed fingerprint verification image. The preprocessing process of the mobile phone for the fingerprint verification image is similar to the image preprocessing operation executed by the mobile phone in the fingerprint input process, and is not described in detail.

The process of determining whether the fingerprint verification image matches the fingerprint templates in the fingerprint template library by the mobile phone may be determined by calculating a matching score (or referred to as a matching value) between the fingerprint verification image and the fingerprint templates in the fingerprint template library. Specifically, if the matching value between the fingerprint verification image and any fingerprint template in the fingerprint template library is greater than or equal to the preset matching value, it indicates that there is a fingerprint template in the fingerprint template library that matches the fingerprint verification image, that is, the current user is the owner user, and the mobile phone can execute S1103. If the matching value between the fingerprint verification image and each fingerprint template in the fingerprint template library is smaller than the preset matching value, it is indicated that there is no fingerprint template matching with the fingerprint verification image in the fingerprint template library, that is, the current user is a non-host user, and the mobile phone can execute S1104. The preset matching value is set according to actual situations, for example, the preset matching value may be 90, 85, etc., which is not limited specifically.

In one implementation, after the fingerprint verification image is collected, for each fingerprint template in the fingerprint template library, the mobile phone may compare the fingerprint verification image with each fingerprint image in the fingerprint template, so as to obtain a similarity between the fingerprint verification image and each fingerprint image. And then, the mobile phone can obtain a matching score according to the multiple similarities and a statistical method. Then, the mobile phone can determine the highest matching score from the matching scores corresponding to the fingerprint templates in the fingerprint template library. And then, under the condition that the highest matching score is larger than or equal to a preset matching value, the mobile phone determines that a fingerprint template matched with the fingerprint verification image exists in the fingerprint template library.

It will be appreciated that the statistical method may be calculated by an average number solution method, may be calculated by a mode solution method, may be calculated by a median solution method, or the like, and is not particularly limited.

In another implementation manner, after the fingerprint verification image is collected, for each fingerprint template in the fingerprint template library, the mobile phone may input the fingerprint verification image and the fingerprint template into a fingerprint matching model to obtain a matching score. Then, the mobile phone can determine the highest matching score from the matching scores corresponding to the fingerprint templates in the fingerprint template library. And then, under the condition that the highest matching score is larger than or equal to a preset matching value, the mobile phone determines that a fingerprint template matched with the fingerprint verification image exists in the fingerprint template library.

S1103, the mobile phone executes unlocking operation.

Specifically, after determining that a fingerprint template matching the fingerprint verification image exists in the fingerprint template library, the mobile phone can execute an unlocking operation.

In an example, as shown in fig. 13, if the fingerprint verification image collected by the mobile phone is successfully matched with the fingerprint templates in the fingerprint template library when the mobile phone is in the screen locking mode, it is indicated that the fingerprint verification is successful, that is, the current user is the owner user, the mobile phone may enter the main interface, that is, the mobile phone may display the main interface 132.

In another example, as shown in fig. 12, if the fingerprint verification image collected by the mobile phone is successfully matched with the fingerprint template in the fingerprint template library in the case that the mobile phone is in the payment mode, it is indicated that the current user is the owner user, and the mobile phone can execute the payment operation and display the interface (b) in fig. 12, where the interface (b) displays text information (such as successful payment), payment amount (such as 13.14) and "complete" control. It can be appreciated that if the "complete" control is clicked by the user, the mobile phone can execute the operation of exiting the current interface according to the clicking operation.

In some embodiments, the handset may also perform an unlocking operation after determining that there is a fingerprint template in the fingerprint template library that matches the fingerprint repair image. That is, whether the fingerprint image before repair or the fingerprint image after repair is matched with any fingerprint template in the fingerprint template library, the current user is the owner user, and the mobile phone can execute unlocking operation, so that not only can the unlocking efficiency of the mobile phone be improved, the situation that the user needs to unlock for many times due to unlocking failure of the mobile phone is reduced, but also the unlocking precision of the mobile phone can be improved, the situation that unlocking failure of the mobile phone occurs due to the situations of finger drying, finger wetting, finger at low temperature and the like is reduced, the success rate of fingerprint identification of the mobile phone is improved, and the use experience of the user is further improved.

S1104, the mobile phone repairs the fingerprint verification image to obtain a fingerprint repair image.

Specifically, after determining that a fingerprint template matched with the fingerprint verification image does not exist in the fingerprint template library, the mobile phone can repair the fingerprint verification image to obtain a fingerprint repair image.

In some embodiments, the mobile phone may repair the fingerprint verification image according to the fingerprint repair model, so as to obtain a fingerprint repair image. The fingerprint restoration model is a graph generation graph (img 2 img) network, and the graph generation graph network is a deep learning model and is used for realizing the function of image restoration by learning a large amount of data. In this embodiment, the fingerprint restoration model may perform restoration processing on an image using an countermeasure generation network. In other embodiments, the fingerprint restoration model may employ a convolutional neural network to perform restoration processing on the image.

In one implementation manner, the training process of the fingerprint repair model may specifically include: the handset obtains a fingerprint dataset. Specifically, as shown in fig. 14, the fingerprint data set includes sub fingerprint data sets in different states, which may be a first sub fingerprint data set in a normal state and a second sub fingerprint data set in an abnormal state, wherein the abnormal state may include at least one of a dry state, a low temperature state, and a wet state. That is, the fingerprint data set comprises a first sub-fingerprint data set and a second sub-fingerprint data set.

It can be understood that, for the training accuracy of the fingerprint repair model, the fingerprint data included in the fingerprint data set may be manually selected, or may be acquired by a mobile phone according to a preset acquisition requirement, which is not particularly limited. The preset acquisition requirements can include that the number of the first sub-fingerprint data sets and the number of the second sub-fingerprint data sets in the fingerprint data sets are the same, the number of the fingerprint data in a dry state, the number of the fingerprint data in a low-temperature state and the number of the fingerprint data in a wet state in the second sub-fingerprint data sets are the same, that is, the preset acquisition requirements can ensure that the number of the fingerprint data in different states is the same, and the number of the different sub-fingerprint data sets is the same, so that not only can the occurrence of the condition that the model training precision is reduced due to unbalanced number of positive and negative samples, but also the occurrence of the condition that the model training efficiency is lower due to excessive number of negative samples (the second sub-fingerprint data sets) can be reduced, the training effect of the model is improved, the generalization capability of the model is improved, and a foundation is provided for generating the fingerprint repair images subsequently.

Specifically, after the fingerprint data set is obtained, the mobile phone can train the pre-constructed fingerprint repair model according to the fingerprint data set and the generated countermeasure network to obtain the trained fingerprint repair model. Wherein the generation countermeasure network (generative adversarial networks, GAN) is a generation model that learns by means of two neural networks opposing each other. The two neural networks are a generation network (generator) for generating generation data similar to the real data and a discrimination network (discriminant) for discriminating the real data from the generation data, respectively. That is, the generation network is in a countermeasure relationship with the discrimination network that supervises the generation data generated by the generation network by the real data to ensure that the generation data finally generated by the generation network is high-quality data, that is, to ensure that the generation data is infinitely close to the real data.

For example, as shown in fig. 15, the mobile phone may input the first sub-fingerprint data set into the generating network to obtain a first generating data set. And then, the mobile phone can respectively input the first generated data set and the second sub-fingerprint data set into the discrimination network to obtain a discrimination result, wherein the discrimination result is used for indicating whether the data in the first generated data set and the second sub-fingerprint data set are real data or not. And then, according to the judging result, the mobile phone can carry out parameter adjustment on the pre-built generation countermeasure network, namely, respectively carrying out parameter updating on the generation network and the judging network until the distribution of the first generation data set and the first sub-fingerprint data set is similar or the first training times reach the first preset times, so as to obtain the trained generation countermeasure network.

Then, as shown in fig. 16, the mobile phone may input the fingerprint data set into a trained generation network to obtain a second generation data set. And then, training the pre-constructed fingerprint restoration model according to the second generated data set and the fingerprint data set by the mobile phone to obtain a loss value corresponding to a preset loss function, wherein the real data corresponding to the generated data are real fingerprint data corresponding to the generated data in the fingerprint data set. And then, the mobile phone can judge whether the fingerprint repair model is trained according to the loss value. Under the condition that the fingerprint repair model is not trained, the mobile phone updates model parameters according to a preset loss function to obtain the fingerprint repair model so as to continue model training. Under the condition that the training of the fingerprint repair model is completed, the mobile phone obtains the trained fingerprint repair model according to the adjusted model parameters. And when the second training times reach the second preset times or the loss value is smaller than the preset loss value, the mobile phone can determine that the training of the fingerprint repair model is completed.

The preset loss function may include at least one of a similarity loss function, an error loss function, a total variation loss function, and an absolute value loss function, where the similarity loss function is a structural similarity (structure similarity index measure, SSIM) loss function, which may be used to measure not only the distortion degree of an image but also the similarity degree of two images. The error loss function is a root mean square error (root mean squared error, RMSE) loss function that is used to measure the root mean square difference between the predicted data and the real data, representing the average degree of deviation between the predicted data and the real data. The Total Variation (TV) loss function is used for carrying out noise reduction processing on the image, and specifically, the mobile phone can reduce the difference between adjacent pixel values in the image by reducing the loss value of the Total Variation loss function, thereby ensuring the smoothness of the image. The absolute value loss function (L1 loss) is used to measure the average absolute error between the predicted data and the true data of the model.

In some embodiments, for each generated data in the second generated data set, the mobile phone may input the generated data into the pre-built fingerprint repair model to obtain the predicted data. And then, the mobile phone can determine the loss value corresponding to the preset loss function according to the real data corresponding to the generated data and the predicted data. And then, the mobile phone can carry out parameter adjustment on the pre-constructed fingerprint repair model according to the loss value until the second training times reach the second preset times or the loss value is smaller than the preset loss value, so as to obtain the trained fingerprint repair model.

S1105, the mobile phone judges whether a fingerprint template matched with the fingerprint repair image exists in the fingerprint template library.

In some embodiments, after obtaining the fingerprint repair image, the mobile phone may continue to determine whether a fingerprint template matching the fingerprint repair image exists in the fingerprint template library, and if the fingerprint template matching the fingerprint repair image exists in the fingerprint template library, it may still be described that the current user is the owner user, and the mobile phone may return to execute S1103. Therefore, the success rate of unlocking the mobile phone can be improved, the occurrence of the situation that normal unlocking cannot be performed due to the fact that the fingerprint images are different is reduced, and the use experience of a user is improved. If there is no fingerprint template matching the fingerprint repair image in the fingerprint template library, it indicates that the current user is a non-host user, and the mobile phone can execute S1106. Therefore, the mobile phone can be prevented from being correspondingly operated by the current user in time, the situation that the non-host user controls the mobile phone is reduced, and the loss of resources (such as property) of the user is avoided.

S1106, the handset does not perform an unlocking operation.

Specifically, after determining that no fingerprint template matching the fingerprint repair image exists in the fingerprint template library, the mobile phone may not perform the unlocking operation. The mobile phone can output prompt information, wherein the prompt information is used for prompting that the fingerprint verification of the current user fails. For example, the mobile phone can display the prompt information through popup windows, interfaces, short messages and the like, or can output the prompt information through voice.

In an example, as shown in fig. 13, if a fingerprint template matched with a fingerprint repair image does not exist in the fingerprint template library in the case that the mobile phone is in the screen locking mode, it is indicated that fingerprint verification fails, that is, the current user is a non-host user, and the mobile phone can continue to display the screen locking interface 131 or display prompt information of fingerprint verification failure on the basis of the screen locking interface 131 for the user to view.

In another example, as shown in fig. 12, in the case that the mobile phone is in the payment mode, if there is no fingerprint template matching the fingerprint repair image in the fingerprint template library, it is indicated that the fingerprint verification fails, that is, the current user is not the owner, the mobile phone may not perform the payment operation, that is, the mobile phone may display the interface (c) in fig. 12, where the interface (c) displays the fingerprint collection area 121, the prompt information of the fingerprint verification failure (such as the fingerprint verification failure, please retry), and the payment amount (such as item 13.14) for the user to continue the fingerprint verification.

In one implementation, the mobile phone can firstly judge whether a fingerprint template matched with the fingerprint verification image exists in the fingerprint template library, and execute the repairing operation of the fingerprint image after determining that the fingerprint template matched with the fingerprint verification image does not exist in the fingerprint template library, so that unnecessary power consumption loss can be reduced, and the utilization rate of repairing resources is improved.

However, in order to improve the execution efficiency of fingerprint identification, after obtaining the fingerprint verification image, the mobile phone may repair the fingerprint verification image first. Then, the mobile phone can judge whether a fingerprint template matched with the repaired fingerprint verification image (or referred to as fingerprint repair image) exists in the fingerprint template library, and if the fingerprint template matched with the fingerprint repair image exists in the fingerprint template library, the mobile phone can execute unlocking operation. If the fingerprint template matched with the fingerprint repair image does not exist in the fingerprint template library, the mobile phone does not execute unlocking operation. Therefore, the time for template matching can be reduced, the step of twice template matching is not needed, the success rate of fingerprint identification can be ensured, the execution efficiency of fingerprint identification is improved, the time for fingerprint identification is reduced, and the use experience of a user is improved.

The method of the embodiment of the present application will be described below by taking an electronic device as a mobile phone and an application scene as a template to update the scene. Specifically, under the condition that the mobile phone can execute the unlocking operation, the mobile phone can judge whether the successfully matched fingerprint image is a repaired fingerprint image, and under the condition that the successfully matched fingerprint image is the repaired fingerprint image, the mobile phone updates the dual-template of the fingerprint template library. For example, as shown in fig. 17, the fingerprint identification method may include S1801 to S1810.

S1801, under the condition that the mobile phone executes unlocking operation, the mobile phone acquires a target fingerprint image.

Specifically, after determining that the mobile phone can perform the unlocking operation, the mobile phone can acquire the target fingerprint image. The target fingerprint image is a fingerprint image successfully matched with any fingerprint template in the fingerprint template library, that is, the target fingerprint image is a fingerprint image capable of enabling the mobile phone to execute unlocking operation.

In some embodiments, the process of performing the unlocking operation by the mobile phone and the process of performing the template updating by the mobile phone may be performed simultaneously or sequentially, which is not limited in particular. For example, the mobile phone may perform the unlocking operation, that is, perform the step of S1103, and then perform the step of updating the template, that is, perform the steps of S1801 to S1810. For another example, the mobile phone may perform the step of updating the template, that is, perform the steps of S1801 to S1810, and then perform the unlocking operation, that is, perform the step of S1103. For another example, the mobile phone may execute steps S1103 and S1801 to S1810 simultaneously.

S1802, the mobile phone judges whether the target fingerprint image is a repaired fingerprint image.

The repaired fingerprint image is obtained by inputting the acquired fingerprint verification image into the fingerprint repair model by the mobile phone. It can be understood that if the target fingerprint image carries a repaired mark, which indicates that the target fingerprint image is a repaired fingerprint image, the mobile phone can determine that the target fingerprint image is a repaired fingerprint image.

In some embodiments, after the target fingerprint image is obtained, the mobile phone may determine whether the target fingerprint image is a repaired fingerprint image, and if the target fingerprint image is a repaired fingerprint image, which indicates that the mobile phone has previously performed a repair operation of the fingerprint image, the mobile phone may perform S1803 to determine whether the fingerprint image before repair and the fingerprint image after repair respectively meet corresponding preset conditions. If the target fingerprint image is not the repaired fingerprint image, which indicates that the mobile phone has not performed the repairing operation of the fingerprint image before, the mobile phone may perform S1808 to determine whether the fingerprint verification image meets the first preset condition.

S1803, the mobile phone acquires a fingerprint verification image.

Specifically, after determining that the target fingerprint image is a repaired fingerprint image, the mobile phone may acquire a fingerprint verification image, that is, acquire a fingerprint image before repair. It can be understood that the fingerprint verification image is a fingerprint image directly collected by the mobile phone through the fingerprint sensor.

It will be appreciated that if the target fingerprint image is a restored fingerprint image, the mobile phone may determine that the target fingerprint image at this time is the fingerprint restored image.

S1804, the mobile phone judges whether the fingerprint verification image meets a first preset condition or not, and judges whether the target fingerprint image meets a second preset condition or not.

Specifically, after the fingerprint verification image is obtained, the mobile phone may respectively determine whether the fingerprint verification image meets a first preset condition, and determine whether the target fingerprint image meets a second preset condition. The first preset condition is used for evaluating whether the fingerprint image before restoration can be updated into the fingerprint template library. The second preset condition is used for evaluating whether the repaired fingerprint image can be updated into the fingerprint template library.

In one implementation, the first preset condition may include at least one of:

(1) The overlapping area between the fingerprint verification image and the target fingerprint template is larger than the preset area. The overlapping area may be an overlapping area between the fingerprint verification image and any fingerprint image in the target fingerprint template, or may be an overlapping area between the fingerprint verification image and a fingerprint image with the highest fingerprint integrity in the target fingerprint template, which is not particularly limited. The preset area can be set according to actual conditions.

(2) The matching value of the fingerprint verification image and the target fingerprint template is larger than a first preset matching value. The matching value may be a matching value between the fingerprint verification image and any fingerprint image in the target fingerprint template, or may be a matching value between the fingerprint verification image and a fingerprint image with the highest fingerprint integrity in the target fingerprint template, which is not particularly limited. The first preset matching value may be set according to actual conditions.

(3) The first combined value between the fingerprint verification image and the target fingerprint template is greater than a first preset combined value. The first combination value is used for evaluating whether the fingerprint verification image can be updated into the fingerprint template library. The first combined value may be determined based on the overlap area and the matching value. Specifically, the handset may calculate a first product between the first weight and the matching value, and calculate a second product between the second weight and the overlapping area. Then, the mobile phone can add the first product and the second product to obtain a first combined value. It is understood that the first weight and the second weight may be the same or different, and are not particularly limited.

The target fingerprint template is the fingerprint template with the highest matching value with the fingerprint verification image in the fingerprint template library.

It should be noted that the first preset condition may include a combination of one or more of the above. If the first preset condition includes a plurality of items, the mobile phone may perform the judgment at the same time, or may perform the judgment according to a preset first execution sequence, which is not particularly limited. For example, the mobile phone may preferably determine whether the overlapping area is greater than a preset area and whether the matching value is greater than a first preset matching value, and determine whether the first combination value is greater than the first preset combination value after determining that the overlapping area is greater than the preset area and the matching value is greater than the first preset matching value. Thus, unnecessary resource loss can be reduced, and the utilization rate of computing resources can be improved.

For example, when the first preset condition includes that the overlapping area is greater than the preset area, the matching value is greater than the first preset matching value, and the first combination value is greater than the first preset combination value, the process of determining, by the mobile phone, whether the fingerprint verification image meets the first preset condition may specifically include: the mobile phone can firstly judge whether the matching value is larger than a first preset matching value, if the matching value is larger than the first preset matching value, the mobile phone can continuously judge whether the overlapping area is larger than a preset area, if the overlapping area is larger than the preset area, the mobile phone can judge whether the first combined value is larger than the first preset combined value, and if the first combined value is larger than the first preset combined value, the mobile phone can determine that the fingerprint verification image meets a first preset condition. Therefore, not only can the occurrence of the condition that the success rate of fingerprint matching is reduced due to image quality be reduced and the rejection rate (false reject rate, FRR) be reduced, but also False Acceptance (FA) caused by the problem of matching values can be avoided, and the use experience of a user is improved. The rejection rate refers to the probability that the owner user is erroneously identified as a non-owner user, and the owner user cannot unlock normally. Error identification refers to the situation where a non-owner user is incorrectly identified as an owner user.

If the matching value is smaller than or equal to a first preset matching value, or the overlapping area is smaller than or equal to a preset area, or the first combination value is smaller than or equal to the first preset combination value, which indicates that the fingerprint verification image does not meet the template updating condition, the mobile phone can determine that the fingerprint verification image does not meet the first preset condition, that is, the mobile phone can judge other conditions without other conditions, so that unnecessary resource loss can be reduced, and the utilization rate of computing resources is improved.

In another implementation, the second preset condition may include at least one of:

(1) The quality score of the target fingerprint image is greater than a preset score. Wherein the quality score is used to characterize the image quality of the target fingerprint image. It can be understood that the higher the quality score of the target fingerprint image, the clearer the image quality of the target fingerprint image is, that is, the better the presentation effect of the target fingerprint image is; the lower the quality score of the target fingerprint image, the more blurred the image quality of the target fingerprint image, i.e. the worse the rendering of the target fingerprint image.

In one implementation manner, the mass fraction of the target fingerprint image may be calculated based on a fingerprint texture in the target fingerprint and a fingerprint area, and specifically, the mobile phone may input the target fingerprint image into the image quality model to obtain the mass fraction of the target fingerprint image.

(2) The highest matching value corresponding to the fingerprint template in the fingerprint template library of the target fingerprint image is larger than the second preset matching value. The second preset matching value can be set according to actual conditions. The second preset matching value may be the same as or different from the first preset matching value, and is not particularly limited.

(3) And a second combination value between the fingerprint template corresponding to the highest matching value and the target fingerprint image is larger than a second preset combination value. The second combination value is used for evaluating whether the target fingerprint image can be updated into the fingerprint template library. The second combined value is determined based on the quality score and the highest matching value. Specifically, the mobile phone may calculate a third product between the third weight and the highest matching value, and calculate a fourth product between the fourth weight and the quality score. And then, the mobile phone can add the third product and the fourth product to obtain a second combined value. It is understood that the third weight and the fourth weight may be the same or different, and are not particularly limited.

It should be noted that the second preset condition may include a combination of one or more of the above. If the second preset condition includes a plurality of items, the mobile phone may perform the judgment at the same time, or may perform the judgment according to a preset second execution sequence, which is not particularly limited. For example, the mobile phone may preferably determine whether the quality score is greater than a preset score and whether the highest matching value is greater than a second preset matching value, and after determining that the quality score is greater than the preset score and the highest matching value is greater than the second preset matching value, the mobile phone may further determine whether the second combination value is greater than the second preset combination value. Thus, unnecessary resource loss can be reduced, and the utilization rate of computing resources can be improved.

The process of determining, by the mobile phone, whether the fingerprint restoration image meets the second preset condition may specifically include: the mobile phone can firstly judge whether the highest matching value is larger than a second preset matching value, if the highest matching value is larger than the second preset matching value, the mobile phone can continuously judge whether the quality score of the target fingerprint image is larger than the preset score, if the quality score of the target fingerprint image is larger than the preset score, the mobile phone can judge whether the second combination value is larger than the second preset combination value, and if the second combination value is larger than the second preset combination value, the mobile phone can determine that the target fingerprint image meets the second preset condition. Therefore, the updating efficiency of the fingerprint template can be improved, and a foundation is provided for accurately and rapidly identifying the fingerprint subsequently.

If the highest matching value is smaller than or equal to a second preset matching value, or the quality score of the target fingerprint image is smaller than or equal to a preset score, or the second combination value is smaller than or equal to a second preset combination value, which indicates that the target fingerprint image does not meet the template updating condition, the mobile phone can determine that the target fingerprint image does not meet the second preset condition, that is, the mobile phone can judge other conditions without other conditions, so that unnecessary resource loss can be reduced, and the utilization rate of computing resources is improved.

In some embodiments, the above process of determining whether the fingerprint verification image meets the first preset condition and the process of determining whether the target fingerprint image meets the second preset condition may be performed by the mobile phone at the same time or performed by the mobile phone according to a preset sequence, which is not limited in particular. For example, the mobile phone may determine whether the fingerprint verification image satisfies the first preset condition, and then determine whether the target fingerprint image satisfies the second preset condition. For another example, the mobile phone may first determine whether the fingerprint repair image meets the second preset condition, and then determine whether the fingerprint verification image meets the first preset condition.

S1805, under the condition that the fingerprint verification image meets the first preset condition, the mobile phone updates the fingerprint verification image into the fingerprint template library.

Specifically, after determining that the fingerprint verification image meets the first preset condition, but the fingerprint repair image does not meet the second preset condition, the mobile phone can update the fingerprint verification image to the fingerprint template library. The mobile phone updates the fingerprint verification image into the fingerprint template library means that the mobile phone takes the fingerprint verification image as a new fingerprint template and adds the new fingerprint template into the fingerprint template library, or the mobile phone deletes one fingerprint template in the fingerprint template library and adds the fingerprint verification image into the fingerprint template library as a new fingerprint template so as to realize template replacement.

In one implementation, after determining that the fingerprint verification image meets the first preset condition, the mobile phone may determine whether the number of fingerprint templates in the fingerprint template library reaches the preset number of templates, if the number of fingerprint templates reaches the preset number of templates, which indicates that the fingerprint templates in the fingerprint template library are sufficient, the mobile phone may delete the candidate fingerprint templates in the fingerprint template library, and add the fingerprint verification image as a new fingerprint template to the fingerprint template library, so as to obtain a new fingerprint template library, that is, the mobile phone may replace the candidate fingerprint templates in the fingerprint template library with the fingerprint verification image, thereby obtaining the new fingerprint template library. If the number of the fingerprint templates does not reach the preset number of templates, indicating that the fingerprint templates in the fingerprint template library are insufficient, the mobile phone can directly take the fingerprint verification image as a new fingerprint template and add the new fingerprint template into the fingerprint template library to obtain a new fingerprint template library.

In some embodiments, the candidate fingerprint template refers to a fingerprint template with the lowest template requirement in the fingerprint template library, and the template requirement is a preset requirement. For example, the template requirements may include at least one of a quality score of the fingerprint template being less than a preset quality score, a match value with the fingerprint verification image being less than a third preset match value, a match value with the fingerprint repair image being less than a fourth preset match value, and a match probability with the fingerprint verification image or the fingerprint repair image being less than a preset probability.

S1806, under the condition that the target fingerprint image meets the second preset condition, the mobile phone updates the target fingerprint image into the fingerprint template library.

Specifically, after determining that the target fingerprint image meets the second preset condition, but the fingerprint verification image does not meet the first preset condition, the mobile phone can update the target fingerprint image into the fingerprint template library. The mobile phone updating the target fingerprint image into the fingerprint template library means that the mobile phone takes the target fingerprint image as a new fingerprint template and adds the new fingerprint template into the fingerprint template library, or the mobile phone deletes one fingerprint template in the fingerprint template library and adds the target fingerprint image into the fingerprint template library as a new fingerprint template so as to realize template replacement.

In one implementation, after determining that the target fingerprint image meets the second preset condition, the mobile phone may determine whether the number of fingerprint templates in the fingerprint template library reaches the preset number of templates, if the number of fingerprint templates reaches the preset number of templates, which indicates that the fingerprint templates in the fingerprint template library are sufficient, the mobile phone may delete the candidate fingerprint templates in the fingerprint template library and add the target fingerprint image to the fingerprint template library, so as to obtain a new fingerprint template library, that is, the mobile phone may replace the candidate fingerprint templates in the fingerprint template library with the target fingerprint image, thereby obtaining the new fingerprint template library. If the number of the fingerprint templates does not reach the preset number of templates, indicating that the fingerprint templates in the fingerprint template library are insufficient, the mobile phone can directly take the target fingerprint image as a new fingerprint template and add the new fingerprint template into the fingerprint template library to obtain a new fingerprint template library.

S1807, under the condition that the fingerprint verification image meets the first preset condition and the target fingerprint image meets the second preset condition, the mobile phone updates the fingerprint verification image and the target fingerprint image into the fingerprint template library.

Specifically, after it is determined that the fingerprint verification image meets the first preset condition and the target fingerprint image meets the second preset condition, the mobile phone may update the fingerprint verification image and the target fingerprint image to the fingerprint template library at the same time, that is, the mobile phone may perform the dual-template updating operation. Thus, the accuracy of the template information can be improved, and the richness of the template information can be increased.

In one implementation, after determining that the fingerprint verification image meets a first preset condition and the target fingerprint image meets a second preset condition, the mobile phone can determine whether the number of fingerprint templates in the fingerprint template library reaches the preset number of templates, if the number of fingerprint templates reaches the preset number of templates, the fingerprint templates in the fingerprint template library are sufficient, the mobile phone can delete at least two fingerprint templates in the fingerprint template library, take the fingerprint verification image and the fingerprint repair image as two new fingerprint templates, and simultaneously add the two new fingerprint templates to the fingerprint template library to obtain a new fingerprint template library.

Specifically, the mobile phone can delete two candidate fingerprint templates in the fingerprint template library, take the fingerprint verification image and the fingerprint restoration image as two new fingerprint templates, and simultaneously add the two new fingerprint templates into the fingerprint template library to obtain a new fingerprint template library, that is, the mobile phone can replace the two candidate fingerprint templates in the fingerprint template library with the fingerprint verification image and the target fingerprint image, thereby obtaining the new fingerprint template library.

If the number of the fingerprint templates does not reach the preset number of templates, the mobile phone can further judge whether the number of the phase differences between the number of the fingerprint templates and the preset number of the templates is larger than 1, if the number of the phase differences between the number of the fingerprint templates and the preset number of the templates is larger than 1, the mobile phone can directly take the fingerprint verification image and the target fingerprint image as two new fingerprint templates, and the two new fingerprint templates are added into the fingerprint template library to obtain a new fingerprint template library. If the difference between the number of the fingerprint templates and the number of the preset templates is equal to 1, the fact that the fingerprint template library has a small template storage space is indicated, and the mobile phone can delete at least one fingerprint template in the fingerprint template library. Then, the mobile phone can take the fingerprint verification image and the target fingerprint image as two new fingerprint templates, and simultaneously add the two new fingerprint templates into the fingerprint template library to obtain a new fingerprint template library.

Specifically, the mobile phone may delete one candidate fingerprint template in the fingerprint template library. Then, the mobile phone can take the fingerprint verification image and the target fingerprint image as two new fingerprint templates, and simultaneously add the two new fingerprint templates into the fingerprint template library to obtain a new fingerprint template library.

It can be understood that the mobile phone updates the fingerprint image before repairing to the fingerprint template library, so that the efficiency of fingerprint identification of the mobile phone can be improved, that is, the mobile phone acquires a similar fingerprint verification image again next time, and the fingerprint identification can be realized without repairing by a fingerprint repairing model. In addition, the mobile phone updates the repaired fingerprint image into the fingerprint template library, so that the image quality of each fingerprint template in the fingerprint template library can reach the preset requirement, further, the fingerprint identification precision can be improved, the situation of mobile phone error identification or missing identification is reduced, and the use experience of a user is improved.

In some embodiments, after it is determined that the fingerprint verification image does not meet the first preset condition and the target fingerprint image does not meet the second preset condition, the mobile phone does not need to update the fingerprint template library, so that the fingerprint images updated into the fingerprint template library can be ensured to be all fingerprint templates meeting the template updating condition, and a foundation is provided for fingerprint identification of subsequent mobile phones.

S1808, the mobile phone judges whether the fingerprint verification image meets a first preset condition.

Specifically, after determining that the target fingerprint image is not the repaired fingerprint image, that is, after determining that the target fingerprint image is the unrepaired fingerprint image, the mobile phone may determine whether the target fingerprint image meets a first preset condition, if the target fingerprint image meets the first preset condition, it is indicated that the target fingerprint image meets a template updating condition, and the mobile phone may execute S1809. If the target fingerprint image does not meet the first preset condition, it is indicated that the target fingerprint image does not meet the template updating condition, and in order to ensure the updating accuracy of the fingerprint template, the mobile phone may execute S1810.

It will be appreciated that if the target fingerprint image is not a post-repair fingerprint image, it is indicated that the target fingerprint image is a pre-repair fingerprint image, that is, the target fingerprint image at this time is the fingerprint verification image.

S1809, the mobile phone updates the target fingerprint image into the fingerprint template library.

Specifically, after determining that the target fingerprint image meets the first preset condition, the mobile phone may update the target fingerprint image to the fingerprint template library. The mobile phone updating the target fingerprint image into the fingerprint template library means that the mobile phone takes the target fingerprint image as a new fingerprint template and adds the new fingerprint template into the fingerprint template library, or the mobile phone deletes one fingerprint template in the fingerprint template library and adds the target fingerprint image into the fingerprint template library as a new fingerprint template so as to realize template replacement. Therefore, the fingerprint identification precision can be improved, the occurrence of the situation of error identification or missing identification of the mobile phone is reduced, and the use experience of a user is improved.

In some embodiments, after determining that the target fingerprint image meets the first preset condition, the mobile phone may determine whether the number of fingerprint templates in the fingerprint template library reaches the preset number of templates, if the number of fingerprint templates reaches the preset number of templates, which indicates that the fingerprint templates in the fingerprint template library are sufficient, the mobile phone may delete the candidate fingerprint templates in the fingerprint template library, and add the target fingerprint image as a new fingerprint template to the fingerprint template library, so as to obtain a new fingerprint template library, that is, the mobile phone may replace the candidate fingerprint templates in the fingerprint template library with the target fingerprint image, so as to obtain a new fingerprint template library. If the number of the fingerprint templates does not reach the preset number of templates, indicating that the fingerprint templates in the fingerprint template library are insufficient, the mobile phone can directly take the target fingerprint image as a new fingerprint template and add the new fingerprint template into the fingerprint template library to obtain a new fingerprint template library.

S1810, the mobile phone does not update the fingerprint template library.

Specifically, after the target fingerprint image is determined to not meet the first preset condition, the mobile phone does not need to update the fingerprint template library. Therefore, the fingerprint images updated into the fingerprint template library can be ensured to be the fingerprint templates which meet the template updating conditions, and a foundation is provided for fingerprint identification of the follow-up mobile phone.

In some embodiments, the present application provides a computer storage medium comprising computer instructions that, when run on an electronic device, cause the electronic device to perform a method of adjusting a usage parameter as described above.

In some embodiments, the present application provides a computer program product which, when run on an electronic device, causes the electronic device to perform the method of adjusting a usage parameter as described above.

It will be apparent to those skilled in the art from this description that, for convenience and brevity of description, only the above-described division of the functional modules is illustrated, and in practical application, the above-described functional allocation may be performed by different functional modules according to needs, i.e. the internal structure of the apparatus is divided into different functional modules to perform all or part of the functions described above.

In the several embodiments provided in this application, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of the modules or units is merely a logical functional division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another apparatus, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.

The units described as separate parts may or may not be physically separate, and the parts displayed as units may be one physical unit or a plurality of physical units, may be located in one place, or may be distributed in a plurality of different places. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

In addition, each functional unit in each embodiment of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.

The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a readable storage medium. Based on such understanding, the technical solution of the embodiments of the present application may be essentially or a part contributing to the prior art or all or part of the technical solution may be embodied in the form of a software product stored in a storage medium, including several instructions for causing a device (may be a single-chip microcomputer, a chip or the like) or a processor (processor) to perform all or part of the steps of the methods described in the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read Only Memory (ROM), a random access memory (random access memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.

The foregoing is merely a specific embodiment of the present application, but the scope of the present application is not limited thereto, and any changes or substitutions within the technical scope of the present disclosure should be covered in the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A method of fingerprint identification, comprising:

responding to touch operation of a user on a fingerprint acquisition area of electronic equipment, and acquiring a fingerprint restoration image by the electronic equipment, wherein the fingerprint restoration image is an image generated after the fingerprint verification image acquired by the electronic equipment is restored;

in the case that a fingerprint template matched with the fingerprint restoration image exists in a fingerprint template library, the electronic device updates the fingerprint verification image and/or the fingerprint restoration image into the fingerprint template library.

2. The method of claim 1, wherein the electronic device updating the fingerprint verification image and/or the fingerprint repair image into the fingerprint template library comprises:

under the condition that the fingerprint verification image meets a first preset condition, the electronic equipment updates the fingerprint verification image into the fingerprint template library; wherein the first preset condition includes at least one of an overlapping area between the fingerprint verification image and a target fingerprint template being greater than a preset area, a matching value of the fingerprint verification image and the target fingerprint template being greater than a first preset matching value, and a first combined value being greater than a first preset combined value; the target fingerprint template is the fingerprint template with the highest matching value with the fingerprint verification image in the fingerprint template library; the first combined value is determined based on the overlap area and the matching value.

3. The method of claim 1, wherein the electronic device updating the fingerprint verification image and/or the fingerprint repair image into the fingerprint template library comprises:

under the condition that the fingerprint repair image meets a second preset condition, the electronic equipment updates the fingerprint repair image into the fingerprint template library; the second preset condition comprises at least one of the mass fraction of the fingerprint restoration image being greater than a preset fraction, the highest matching value of the fingerprint restoration image corresponding to a fingerprint template in the fingerprint template library being greater than a second preset matching value, and the second combined value being greater than a second preset combined value; the second combined value is determined based on the quality score and the highest match value.

4. The method of claim 1, wherein the electronic device updating the fingerprint verification image and/or the fingerprint repair image into the fingerprint template library comprises:

and under the condition that the fingerprint verification image meets a first preset condition and the fingerprint restoration image meets a second preset condition, the electronic equipment updates the fingerprint verification image and the fingerprint restoration image into the fingerprint template library.

5. The method of claim 4, wherein the electronic device updating the fingerprint verification image and the fingerprint repair image into the fingerprint template library comprises:

under the condition that the number of fingerprint templates in the fingerprint template library reaches the preset template number, deleting at least two fingerprint templates in the fingerprint template library by the electronic equipment;

the electronic device adds the fingerprint verification image and the fingerprint repair image to the fingerprint template library.

6. The method of claim 5, wherein the method further comprises:

when the number of fingerprint templates in the fingerprint template library does not reach the preset template number and the difference between the fingerprint template number and the preset template number is greater than 1, the electronic device adds the fingerprint verification image and the fingerprint repair image to the fingerprint template library; or,

when the number of fingerprint templates in the fingerprint template library does not reach the preset template number and the difference between the fingerprint template number and the preset template number is equal to 1, deleting at least one fingerprint template in the fingerprint template library by the electronic equipment;

7. The method of any of claims 1-6, wherein the electronic device acquiring a fingerprint repair image comprises:

the electronic equipment collects the fingerprint verification image;

and under the condition that no fingerprint template matched with the fingerprint verification image exists in the fingerprint template library, the electronic equipment restores the fingerprint verification image according to a fingerprint restoration model to obtain the fingerprint restoration image.

8. The method of claim 7, wherein the fingerprint repair model is derived based on a fingerprint dataset and generating a countermeasure network, wherein the fingerprint dataset comprises a first sub-fingerprint dataset comprising a plurality of fingerprint data in a normal state and a second sub-fingerprint dataset comprising a plurality of fingerprint data in an abnormal state, the first sub-fingerprint dataset having the same number of data as the second sub-fingerprint dataset.

9. An electronic device comprising a display screen, a memory, and one or more processors; the display screen, the memory and the processor are coupled; the display screen is used for displaying a fingerprint acquisition area, and the memory is used for storing computer program codes, and the computer program codes comprise computer instructions; the computer instructions, when executed by the processor, cause the electronic device to perform the method of any one of claims 1 to 8.

10. A computer readable storage medium comprising computer instructions which, when run on an electronic device, cause the electronic device to perform the method of any one of claims 1 to 8.