WO2017143571A1

WO2017143571A1 - Fingerprint identification method, device, and terminal

Info

Publication number: WO2017143571A1
Application number: PCT/CN2016/074583
Authority: WO
Inventors: 钟志鑫; 王信亮; 余旖; 李顺展
Original assignee: 深圳市汇顶科技股份有限公司
Priority date: 2016-02-25
Filing date: 2016-02-25
Publication date: 2017-08-31
Also published as: CN106104574A; CN106104574B

Abstract

A fingerprint identification method, device, and terminal. The fingerprint identification method comprises: collecting a fingerprint image (S11); extracting a feature from the fingerprint image (S12); determining, on the basis of the feature, whether a candidate being tested is a living entity (S13); and if the candidate being tested is a living entity, then matching the fingerprint and acquiring a fingerprint matching result (S14). This method can help improve a security of a fingerprint identification process.

Description

Fingerprint identification method, device and terminal

Technical field

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

Background technique

As a unique feature of the human body, fingerprints have lifetime invariance, uniqueness and convenience. Nowadays, fingerprint recognition technology has been widely used in acquisition systems, access control systems, smart phones, smart phones and other devices. With the continuous popularization of payment functions in smart phones, fingerprint recognition technology is further applied to application functions such as online fingerprint payment based on fingerprint unlocking of smart phones.

In the related art, the fingerprint recognition technology generally adopts the fingerprint texture feature in the fingerprint image. However, the illegal user can fake the fake fingerprint according to the acquired fingerprint texture feature, and use the fake fake fingerprint to crack the fingerprint recognition system, thereby causing insufficient security.

Summary of the invention

The present invention aims to solve at least one of the technical problems in the related art to some extent.

To this end, an object of the present invention is to provide a fingerprint recognition method which can improve the security of fingerprint recognition.

Another object of the present invention is to provide a fingerprint recognition apparatus.

Another object of the present invention is to provide a terminal.

In order to achieve the above object, a fingerprint identification method according to the first aspect of the present invention includes: collecting a fingerprint image; extracting features in the fingerprint image; determining, according to the feature, whether the to-be-verified person is a living body; In vivo, fingerprint matching is performed to obtain a fingerprint matching result.

The fingerprint identification method provided by the first aspect of the present invention can prevent the illegal user from using the fake fingerprint to crack the fingerprint identification system by performing the living body detection before the fingerprint matching, thereby improving the security of the fingerprint identification.

In order to achieve the above object, a fingerprint identification device according to a second aspect of the present invention includes: an acquisition module for collecting a fingerprint image; an extraction module for extracting features in the fingerprint image; and a living body recognition module for The feature determines whether the person to be verified is a living body; the fingerprint matching module is configured to perform fingerprint matching when the person to be verified is a living body, and obtain a fingerprint matching result.

The fingerprint identification device provided by the embodiment of the second aspect of the present invention can prevent the illegal user from using the fake fingerprint to crack the fingerprint identification system by performing the live detection before the fingerprint matching, thereby improving the security of the fingerprint recognition.

In order to achieve the above object, a terminal according to a third aspect of the present invention includes a housing, a processor, a memory, a circuit board, and a power supply circuit, wherein the circuit board is disposed inside a space enclosed by the housing, the processor and the memory. Provided on a circuit board; a power supply circuit for supplying power to each circuit or device of the terminal; a memory for storing executable program code; the processor running to correspond to the executable program code by reading executable program code stored in the memory a program for performing the following steps: collecting a fingerprint image; extracting features in the fingerprint image; determining, according to the feature, whether the person to be verified is a living body; if the person to be verified is a living body, performing fingerprint matching to obtain a fingerprint matching result .

The terminal proposed by the third embodiment of the present invention can prevent the illegal user from using the fake fingerprint to crack the fingerprint identification system by performing the live detection before the fingerprint matching, thereby improving the security of the fingerprint identification.

In order to achieve the above object, a non-volatile computer storage medium according to an embodiment of the present invention includes: collecting a fingerprint image; extracting features in the fingerprint image; and determining, according to the feature, whether the to-be-verified person is a living body; The person to be verified is a living body, and fingerprint matching is performed to obtain a fingerprint matching result.

The non-volatile computer storage medium provided by the embodiment of the fourth aspect of the present invention can prevent the illegal user from using the fake fingerprint to crack the fingerprint identification system by performing the live detection before the fingerprint matching, thereby improving the security of the fingerprint recognition.

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

DRAWINGS

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

1 is a schematic flow chart of a fingerprint identification method according to an embodiment of the present invention;

2a-2b are schematic diagrams showing the arrangement of a fingerprint sensor in an embodiment of the present invention;

3 is a schematic view showing deformation of a real finger in a pressing process according to an embodiment of the present invention;

4 is a diagram showing relationship between peak-to-peak value and pressure of a fingerprint corresponding to a real fingerprint and a fake fingerprint, respectively, in an embodiment of the present invention;

FIG. 5 is a schematic flow chart of a living body detection according to an embodiment of the present invention; FIG.

6 is a schematic flow chart of another living body detection in an embodiment of the present invention;

Figure 7 is a schematic view showing the characteristics of a sweat hole in an embodiment of the present invention;

8 is a schematic flow chart of another living body detection in an embodiment of the present invention;

9 is a schematic diagram of a correlation grayscale image of a real fingerprint and a fake fingerprint in an embodiment of the present invention;

10 is a schematic diagram showing the relationship between the residual noise mean square error and the statistical number corresponding to the real fingerprint and the fake fingerprint in the embodiment of the present invention;

11 is a schematic flow chart of another living body detection in an embodiment of the present invention;

FIG. 12 is a schematic flowchart diagram of a fingerprint identification method according to another embodiment of the present invention; FIG.

FIG. 13 is a schematic structural diagram of a fingerprint identification apparatus according to another embodiment of the present invention; FIG.

FIG. 14 is a schematic structural diagram of a fingerprint identification apparatus according to another embodiment of the present invention; FIG.

FIG. 15 is a schematic structural diagram of a terminal according to another embodiment of the present invention.

detailed description

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

FIG. 1 is a schematic flow chart of a fingerprint identification method according to an embodiment of the present invention.

Referring to Figure 1, the method includes:

S11: Acquire a fingerprint image.

The person to be verified can put a finger on the sensor for collecting fingerprints of the terminal, so that the sensor can collect the fingerprint image of the person to be verified.

For example, taking the terminal as a mobile phone as an example, referring to FIG. 2a or FIG. 2b, a fingerprint sensor may be set in the home screen button 21 of the mobile phone to collect a fingerprint image, or may be set in the preset chip 22 on the back of the mobile phone. A fingerprint sensor that captures a fingerprint image.

S12: Extract features in the fingerprint image.

Wherein, the feature may include one or more of the following:

Fingerprint texture features, sweat hole characteristics, residual noise characteristics, peak-to-peak characteristics.

For example, after the fingerprint sensor acquires the fingerprint image, the fingerprint image may be transmitted to the module for feature extraction, and the fingerprint feature is extracted from the fingerprint image by the module for feature extraction.

In this embodiment, the module for feature extraction is located in the terminal. For example, it can be understood that the method in this embodiment can also be applied to the scenario where the client interacts with the server, and the feature can be extracted by the server. And subsequent verification.

S13: Determine, according to the feature, whether the person to be verified is a living body.

Depending on the scenario, different ways can be used to determine whether the person to be verified is a living body.

In some embodiments, the peak-to-peak feature extracted from the fingerprint image can be utilized for live recognition.

Referring to FIG. 3, the real finger will have a slight deformation during the change of the pressing force, and the relative distance between the fingerprint peak 31 and the fingerprint valley 32 will change, that is, the peak-to-peak value of the real fingerprint image will change regularly, and the prosthetic fingerprint Will not exhibit the same regular changes.

Referring to Figure 4, a plot 41 of the true fingerprint peak-to-peak versus pressure is given, along with a plot 42 of the prosthetic fingerprint peak-to-peak versus pressure. It can be seen from Fig. 4 that the peak-to-peak value of the real fingerprint will change significantly with the increase of the pressure, and the peak-to-peak value of the fingerprint has no obvious change with the increase of the pressure.

Based on the peak-to-peak characteristics of the real fingerprint and the prosthetic fingerprint, the living body can be identified as follows.

In some embodiments, referring to FIG. 5, the process of acquiring a fingerprint image, extracting features in the fingerprint image, and detecting the living body includes:

S51: acquiring a first fingerprint image and a second fingerprint image, wherein the first fingerprint image is generated by the first verification pressure by the to-be-verified person, and the second fingerprint image is generated by the second verification pressure by the to-be-verified person, the first pressing The pressure is less than the second pressing pressure.

Since the first pressing pressure is less than the second pressing pressure, the first fingerprint image is a fingerprint image that is collected after the fingerprint controller is lightly pressed by the to-be-verified person, and the second fingerprint image is a fingerprint image that is collected after the fingerprinting sensor is pressed by the verification object. .

For example, before collecting the fingerprint image, the terminal may display a prompt message to the person to be verified, for example, prompting the person to be verified to lightly press or repress, thereby collecting the fingerprint image generated by the person to be verified after gently pressing or repressing the fingerprint sensor.

S52: Extract a first fingerprint peak-to-peak value in the first fingerprint image, and extract a second fingerprint peak-to-peak value in the second fingerprint image.

The first fingerprint peak-to-peak value is the difference between the fingerprint peak and the fingerprint valley in the first fingerprint image, and the second fingerprint peak-to-peak value is the difference between the fingerprint peak and the fingerprint valley in the second fingerprint image.

After the fingerprint image is acquired, it can be extracted and extracted from the peak-to-peak value of the fingerprint.

S53: Calculate a difference between the first fingerprint peak-to-peak value and the second fingerprint peak-to-peak value.

After extracting the peak-to-peak values of the two fingerprints, the difference between the two can be calculated by subtraction.

S54: Determine whether the difference is greater than a preset difference threshold. If yes, execute S55. Otherwise, execute S56.

The difference threshold may be preset according to an empirical value or the like. After the difference is obtained, the difference and the difference threshold may be compared to obtain a determination result.

S55: Determine that the person to be verified is a living body.

S56: Determine that the person to be verified is a prosthesis.

In this embodiment, whether the person to be verified is a living body can be detected by the peak-to-peak value of the fingerprint according to the light pressure and the heavy pressure.

In some embodiments, referring to FIG. 6, the process of acquiring a fingerprint image, extracting features in the fingerprint image, and detecting the living body includes:

S61: Collecting fingerprint images continuously, the continuous fingerprint images are generated by the subject to be verified by pressing pressure of alternating magnitudes.

For example, before collecting the fingerprint image, the terminal may display a prompt message to the person to be verified, for example, prompting the person to be verified to lightly press-press-pressure, thereby collecting the pressure to be verified by the person to be verified. The way to produce a continuous fingerprint image.

S62: extracting a fingerprint peak value and a fingerprint valley value in each fingerprint image, and calculating a peak-to-valley difference between the fingerprint peak value and the fingerprint valley value, that is, a peak-to-peak value, and an inverse change between the statistical peak-to-peak value and the pressing pressure. The number of times.

Among them, the reverse change means that the larger the pressing pressure is, the smaller the peak value is, or the smaller the pressing pressure is, the larger the peak value is.

By counting the peak-to-peak value of each fingerprint image and the corresponding pressing pressure, the number of reverse changes can be obtained.

S63: Determine whether the number of times of the reverse change is greater than a preset number of times threshold, and if yes, execute S64; otherwise, execute S65.

The threshold of the number of times may be preset according to an empirical value or the like. After the difference is obtained, the number of times of the reverse change and the threshold of the number of times may be compared to obtain a determination result.

S64: Determine that the person to be verified is a living body.

S65: Determine that the person to be verified is a prosthesis.

In the present embodiment, whether or not the person to be verified is a living body can be detected by the number of times of the reverse change between the peak-to-peak value and the pressing pressure.

In some embodiments, the perforation features extracted from the fingerprint image can be utilized for live recognition.

Referring to Fig. 7, which is a schematic view of the sweat hole feature of the fingerprint image, an overall schematic 71 of the sweat hole feature and a partially enlarged partial schematic 72 are given. When the user registers the fingerprint, the sweat hole characteristics of the fingerprint can be recorded at the same time. At the time of making a fake fingerprint, the sweat hole characteristic information of the fingerprint image is basically lost due to limitations of the material to be produced and errors in production. Thereby, living body recognition can be performed according to the characteristics of the sweat hole.

Referring to FIG. 8, the process of acquiring a fingerprint image, extracting features in the fingerprint image, and detecting the living body includes:

S81: Acquire a fingerprint image.

For example, the person to be verified places a finger on the fingerprint sensor, so that the fingerprint sensor collects the person to be verified. Fingerprint image.

S82: extracting a sweat hole feature in the fingerprint image.

The characteristics of the sweat hole include: the number of sweat holes, the relative position information of the sweat hole and the fingerprint pattern, and the like.

S83: Determine whether the extracted sweat hole feature and the pre-stored sweat hole feature are within a preset error range, and if yes, execute S84; otherwise, execute S85.

Among them, the sweat hole feature can be obtained and recorded when the user registers.

In addition, if a plurality of sweat hole features are stored in advance, the judgment result is consistent when the extracted sweat hole features are set to match any of the previously selected sweat hole features according to actual scenes. Alternatively, the storage user identifier and the sweat hole feature may be associated with the storage, and the login is performed before the verification is performed. When the verification is performed, the user corresponding to the to-be verified may be obtained from the pre-stored information according to the user identifier of the to-be-verified person. The hole characteristics, and then the extracted sweat hole characteristics and the sweat hole characteristics corresponding to the user identification, when the two are consistent, the judgment result is consistent.

S84: Determine that the person to be verified is a living body.

S85: Determine that the person to be verified is a prosthesis.

In this embodiment, it is possible to detect whether the person to be verified is a living body according to the characteristics of the sweat hole.

In some embodiments, the residual noise features extracted from the fingerprint image may be utilized for live recognition.

Referring to Figure 9, is a schematic diagram of a correlated grayscale image of a real fingerprint and a fake fingerprint. They are the grayscale 911 of the real fingerprint, the grayscale 912 after the real fingerprint denoising, the residual noise grayscale 913 of the real fingerprint, the grayscale 921 of the 2D fake fingerprint, the grayscale 922 of the 2D false fingerprint, and the 2D fake fingerprint. Residual noise grayscale 923, grayscale 931 of 3D fake fingerprint, 3D false fingerprint denominated grayscale 932, 3D false fingerprint residual noise grayscale 933. It can be seen that false fingerprints are easy to introduce high frequency noise during the production process.

Referring to FIG. 10, the relationship between the residual noise mean square error of the real fingerprint and the statistical number 101, the residual noise mean square error of the fake fingerprint and the statistical number 102 and the residual noise mean square difference of the 3D false fingerprint and the statistical number Relationship curve 103. It can be seen from Fig. 10 that the residual noise of the real fingerprint has a small variance.

In some embodiments, referring to FIG. 11, the process of acquiring a fingerprint image, extracting features in the fingerprint image, and detecting the living body includes:

S111: Acquire a fingerprint image.

For example, the person to be verified places a finger on the fingerprint sensor, so that the fingerprint image of the person to be verified is collected by the fingerprint sensor.

S112: Extracting residual noise features in the fingerprint image.

After the fingerprint image is collected, the fingerprint image may be subjected to median filtering to obtain a filtered fingerprint image, and then the difference between the filtered fingerprint image and the filtered fingerprint image may be calculated to obtain residual noise. Sign.

S113: Calculate the mean square error of the residual noise according to the residual noise characteristic.

S114: Determine whether the mean square error of the residual noise is less than a preset mean square error threshold, and if yes, execute S115; otherwise, execute S116.

The mean square error threshold may be preset according to an empirical value or the like. After obtaining the mean square error of the residual noise, the mean square error of the residual noise and the preset mean square error threshold may be compared to obtain a determination result.

S115: Determine that the person to be verified is a living body.

S116: Determine that the person to be verified is a prosthesis.

In this embodiment, whether the person to be verified is a living body can be detected according to the residual noise characteristic.

After detecting whether the person to be verified is a living body through the above process, the following process can also be performed:

S14: If the person to be verified is a living body, perform fingerprint matching to obtain a fingerprint matching result.

For example, after detecting that the person to be verified is a living body, the fingerprint texture feature can be extracted from the fingerprint image, and in addition, the fingerprint texture feature can be acquired and recorded when the user registers. Fingerprint matching is to compare the currently extracted fingerprint texture features with pre-recorded fingerprint texture features. When the two are consistent (same or within the same error range), the fingerprint matching result is fingerprint matching, otherwise the fingerprint does not match. .

Of course, it can be understood that, in this embodiment, fingerprint matching is used for matching in fingerprint matching, and other features may be used for matching. For example, fingerprint matching can also be performed using features employed in living body detection.

Further, after obtaining the fingerprint matching result, the corresponding operation may be performed according to the fingerprint matching result. For example, when the fingerprint matching result is a fingerprint matching, the person to be verified may be allowed to perform a corresponding operation, for example, a fingerprint unlocking terminal, a fingerprint payment, a fingerprint input, a fingerprint login, and the like. If the fingerprint matching result does not match, the corresponding operation can be rejected.

On the other hand, if the person to be verified is not a living body, the fingerprint identification process can be ended, and subsequent fingerprint matching is not performed, and information such as verification failure is directly fed back.

Of course, it can be understood that the living body detection and the fingerprint matching can also be performed in parallel, that is, the fingerprint texture feature, the peak-to-peak feature, the sweat hole feature or the residual noise feature are extracted in the fingerprint image at the same time, and the living body judgment and the fingerprint matching are simultaneously performed. When it is determined that the person to be verified is a living body and the fingerprint matches, the corresponding person is allowed to perform the corresponding operation; when it is determined that the person to be verified is a prosthesis or the fingerprint matching fails, the information such as the verification failure is fed back. Therefore, while the living body detection is increased, the time of the original fingerprint matching is not increased.

In this embodiment, by performing the living body detection before the fingerprint matching, the illegal user can be prevented from using the fake fingerprint to crack the fingerprint identification system, thereby improving the security of the fingerprint identification. In addition, by collecting fingerprint images, directly root According to the fingerprint image for living body detection, the fraudulent method of the real living fake fingerprint can be avoided, and the safety is further improved. In addition, by performing live detection directly from the fingerprint image, it is possible to avoid additional hardware costs and improve compatibility. Further, by the above-described different methods of living body detection, diversification and flexibility of the living body detection method can be achieved.

FIG. 12 is a schematic flow chart of a fingerprint identification method according to another embodiment of the present invention.

Referring to Figure 12, the method includes:

S121: Determine the security level used by the current application.

Among them, different applications (Application, APP) can set different security levels.

For example, the security level can be divided into I, II, and III, and is sequentially increased in the order of I, II, and III. In the application scenario of Level I security requirements, it is not necessary to perform live detection, and fingerprint matching is performed only according to fingerprint texture features. In the application scenario of Level II security, the process of living body detection is added on the basis of the level I safety, and the living body detection is performed according to the characteristics of the sweat hole and/or the residual noise characteristics. In the application scenario of Level III security requirements, the user is required to press different strengths to extract the peak-to-peak characteristics of the fingerprint, and then perform the living body detection according to the peak-to-peak characteristics. In the case of the III-level safety requirement, only the peak may be used for the living body detection. The peak feature, or it may be based on a level II security level, ie, based on peak-to-peak characteristics during live detection, and also based on sweat feature and/or residual noise characteristics.

S122: Determine whether the living body detection is required according to the currently used security level. If yes, execute S123; otherwise, execute S126.

For example, if the security level is level II or level III, in vivo detection is required, and if it is level I, in vivo detection is not required.

S123: Acquire a fingerprint image according to the currently used security level.

For example, if the security level is level II, the normal fingerprint collection method may be adopted, and the fingerprint image is collected after the fingerprint is placed on the fingerprint sensor by the person to be verified.

For another example, if the security level is level III, since a fingerprint image of different pressing pressures needs to be collected, a prompt message may be displayed to the person to be verified, for example, prompting the person to be verified to lightly press or press, or lightly pressing-heavy-light The pressure is alternately pressed to collect a fingerprint image generated by the person to be verified using different pressing pressures.

S124: Extract features corresponding to the security level in the fingerprint image.

Among them, different features can be extracted according to different security levels.

For example, if the security level is level II, the sweat hole feature or residual noise characteristics can be extracted.

If the security level is level III, the peak-to-peak feature can be extracted.

S125: Determine whether it is a living body according to the extracted feature, if yes, execute S126, otherwise, execute S127.

For the in vivo detection method, refer to the related description in the above embodiment, and the detailed description is not provided herein.

S126: Perform fingerprint matching.

For example, the fingerprint texture features are extracted from the fingerprint image and compared with the pre-stored fingerprint texture features. If they are identical or within the error range, the fingerprint matching result is a fingerprint matching, otherwise the fingerprint matching result is not matched. Then, the corresponding operation can be performed according to the fingerprint matching result. For example, when the fingerprint is matched, the person to be verified is allowed to perform subsequent operations, for example, fingerprint unlocking, fingerprint payment, fingerprint entry, fingerprint login, and the like. If the fingerprints do not match, the person to be verified may be refused to perform subsequent operations, and the fingerprint unmatched information is fed back to the person to be verified.

S127: Determine that the person to be verified is a prosthesis.

For example, the prosthesis information can be fed back to the person to be verified. After that, the verification process can be ended, and the person to be verified is not allowed to perform subsequent fingerprint unlocking operations.

In this embodiment, by performing the living body detection before the fingerprint matching, the illegal user can be prevented from using the fake fingerprint to crack the fingerprint identification system, thereby improving the security of the fingerprint identification. In addition, by collecting the fingerprint image and performing the living body detection directly according to the fingerprint image, the fraudulent method of the real living fake fingerprint can be avoided, and the security is further improved. In addition, by performing live detection directly from the fingerprint image, it is possible to avoid additional hardware costs and improve compatibility. Further, by the above-described different methods of living body detection, diversification and flexibility of the living body detection method can be achieved. In addition, in this embodiment, by selecting a corresponding security level according to different application scenarios, the actual requirements can be better met.

FIG. 13 is a schematic structural diagram of a fingerprint identification apparatus according to another embodiment of the present invention. Referring to FIG. 13, the apparatus 130 includes an acquisition module 131, an extraction module 132, a living body identification module 133, and a fingerprint matching module 134.

The collecting module 131 is configured to collect a fingerprint image;

An extracting module 132, configured to extract features in the fingerprint image;

The living body identification module 133 is configured to determine, according to the feature, whether the person to be verified is a living body;

The fingerprint matching module 134 is configured to perform fingerprint matching when the person to be verified is a living body, and obtain a fingerprint matching result.

In some embodiments, the fingerprint image includes: a first fingerprint image generated by the first verification pressure and a second fingerprint image generated by the second verification pressure generated by the to-be-verified person. The first pressing pressure is less than the second pressing pressure;

The extracted features include: a first fingerprint peak-to-peak value extracted from the first fingerprint image, and a second fingerprint peak-to-peak value extracted from the second fingerprint image;

The living body identification module 133 is specifically configured to:

Calculating a difference between a peak value of the first fingerprint and a peak-to-peak value of the second fingerprint;

If the difference is greater than the preset difference threshold, it is determined that the person to be verified is a living body.

In some embodiments, the fingerprint image includes: a fingerprint image generated by the to-be-verified person using alternating pressing pressures;

The extracted features include: a peak-to-peak value of the fingerprint extracted in each fingerprint image;

The living body identification module 133 is specifically configured to:

Counting the number of times the peak-to-peak value is inversely changed from the pressing pressure;

If the number of reverse changes is greater than a preset number of times threshold, it is determined that the person to be verified is a living body.

In some embodiments, the extracted features are: sweat hole characteristics;

The living body identification module 133 is specifically configured to:

Determining whether the sweat hole feature extracted from the fingerprint image and the pre-stored sweat hole feature are within a preset error range;

If it is within the preset error range, it is determined that the person to be verified is a living body.

In some embodiments, the extracted features are: residual noise characteristics;

The living body identification module 133 is specifically configured to:

Calculating the mean square error of the residual noise according to the residual noise characteristics;

If the mean square error is less than the preset mean square error threshold, it is determined that the person to be verified is a living body.

In some embodiments, referring to Figure 14, the apparatus further includes:

A determination module 135 is configured to determine a security level used by the current application.

The extraction module 132 is specifically configured to:

Features corresponding to the security level are extracted in the fingerprint image.

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

In this embodiment, by performing the living body detection before the fingerprint matching, the illegal user can be prevented from using the fake fingerprint to crack the fingerprint identification system, thereby improving the security of the fingerprint identification. In addition, by collecting the fingerprint image and performing the living body detection directly according to the fingerprint image, the fraudulent method of the real living fake fingerprint can be avoided, and the security is further improved. In addition, by performing live detection directly from the fingerprint image, it is possible to avoid additional hardware costs and improve compatibility. Further, by the above-described different methods of living body detection, diversification and flexibility of the living body detection method can be achieved.

FIG. 15 is a schematic structural diagram of a terminal according to another embodiment of the present invention. Referring to FIG. 15, the terminal 150 includes: a casing, a processor, a memory, a circuit board, and a power supply circuit, wherein the circuit board is disposed inside the space enclosed by the casing, the processor and the memory are disposed on the circuit board; and the power circuit is used The power is supplied to each circuit or device of the terminal; the memory is used to store executable program code; the processor runs the program corresponding to the executable program code by reading the executable program code stored in the memory for performing the following steps:

Collecting fingerprint images;

Extracting features in the fingerprint image;

Determining whether the person to be verified is a living body according to the characteristics;

If the person to be verified is a living body, fingerprint matching is performed to obtain a fingerprint matching result.

In addition, another embodiment of the present invention also provides a non-volatile computer storage medium storing one or more modules for performing the following steps:

Collecting fingerprint images;

Extracting features in the fingerprint image;

It can be understood that the specific content of the terminal and the non-volatile computer storage medium of the foregoing embodiment can be referred to the related description in the method embodiment, and will not be described in detail herein.

It should be noted that in the description of the present invention, the terms "first", "second" and the like are used for descriptive purposes only, and are not to be construed as indicating or implying relative importance. Further, in the description of the present invention, the meaning of "a plurality" means at least two unless otherwise stated.

Any process or method description in the flowcharts or otherwise described herein may be understood to represent a module, segment or portion of code that includes one or more executable instructions for implementing the steps of a particular logical function or process. And the scope of the preferred embodiments of the invention includes additional implementations, in which the functions may be performed in a substantially simultaneous manner or in an opposite order depending on the functions involved, in the order shown or discussed. It will be understood by those skilled in the art to which the embodiments of the present invention pertain.

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

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

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

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

In the description of the present specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" and the like means a specific feature described in connection with the embodiment or example. A structure, material or feature is included in at least one embodiment or example of the invention. In the present specification, the schematic representation of the above terms does not necessarily mean the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in a suitable manner in any one or more embodiments or examples.

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

Claims

A fingerprint identification method, comprising:

Collecting fingerprint images;

Extracting features in the fingerprint image;

Determining, according to the feature, whether the person to be verified is a living body;

If the person to be verified is a living body, fingerprint matching is performed to obtain a fingerprint matching result.
The method of claim 1 wherein

The fingerprint image includes: a first fingerprint image generated by the first verification pressure, and a second fingerprint image generated by the second verification pressure generated by the to-be-verified person. The first pressing pressure is less than the second pressing pressure;

The feature includes: a first fingerprint peak-to-peak value extracted from the first fingerprint image, and a second fingerprint peak-to-peak value extracted from the second fingerprint image;

Determining whether the person to be verified is a living body according to the feature includes:

Calculating a difference between the first fingerprint peak-to-peak value and the second fingerprint peak-to-peak value;

If the difference is greater than a preset difference threshold, it is determined that the person to be verified is a living body.
The method of claim 1 wherein

The fingerprint image includes: a fingerprint image generated by an unverified person using alternating pressing pressures;

The feature includes: a peak-to-peak value of the fingerprint extracted in each fingerprint image;

Determining whether the person to be verified is a living body according to the feature includes:

Counting the number of times the peak-to-peak value is inversely changed from the pressing pressure;

If the number of the reverse changes is greater than a preset number of times threshold, it is determined that the person to be verified is a living body.
The method of claim 1 wherein

The feature is: sweat hole characteristics;

Determining whether the person to be verified is a living body according to the feature includes:

Determining whether the sweat hole feature extracted from the fingerprint image and the pre-stored sweat hole feature are within a preset error range;

If it is consistent within the preset error range, it is determined that the person to be verified is a living body.
The method of claim 1 wherein

The feature is: residual noise characteristics;

Determining whether the person to be verified is a living body according to the feature includes:

Calculating the mean square error of the residual noise according to the residual noise characteristics;

If the mean square error is less than a preset mean square error threshold, it is determined that the person to be verified is a living body.
The method according to any one of claims 1 to 5, further comprising: before the acquiring the fingerprint image:

Determine the level of security used by the current application;

The extracting the feature in the fingerprint image is specifically:

Features corresponding to the security level are extracted in the fingerprint image.
A fingerprint identification device, comprising:

An acquisition module for collecting fingerprint images;

An extraction module, configured to extract features in the fingerprint image;

a living body identification module, configured to determine, according to the feature, whether the person to be verified is a living body;

The fingerprint matching module is configured to perform fingerprint matching when the person to be verified is a living body, and obtain a fingerprint matching result.
The device of claim 7 wherein:

The fingerprint image includes: a first fingerprint image generated by the first verification pressure, and a second fingerprint image generated by the second verification pressure generated by the to-be-verified person. The first pressing pressure is less than the second pressing pressure;

The feature includes: a first fingerprint peak-to-peak value extracted from the first fingerprint image, and a second fingerprint peak-to-peak value extracted from the second fingerprint image;

The living body identification module is specifically configured to:

Calculating a difference between the first fingerprint peak-to-peak value and the second fingerprint peak-to-peak value;

If the difference is greater than a preset difference threshold, it is determined that the person to be verified is a living body.
The device of claim 7 wherein:

The fingerprint image includes: a fingerprint image generated by an unverified person using alternating pressing pressures;

The feature includes: a peak-to-peak value of the fingerprint extracted in each fingerprint image;

The living body identification module is specifically configured to:

Counting the number of times the peak-to-peak value is inversely changed from the pressing pressure;

If the number of the reverse changes is greater than a preset number of times threshold, it is determined that the person to be verified is a living body.
The device of claim 7 wherein:

The feature is: sweat hole characteristics;

The living body identification module is specifically configured to:

Determining whether the sweat hole feature extracted from the fingerprint image and the pre-stored sweat hole feature are within a preset error range;

If it is within the preset error range, it is determined that the person to be verified is a living body.
The device of claim 7 wherein:

The feature is: residual noise characteristics;

The living body identification module is specifically configured to:

Calculating the mean square error of the residual noise according to the residual noise characteristics;

If the mean square error is less than a preset mean square error threshold, it is determined that the person to be verified is a living body.
The device according to any one of claims 7 to 11, further comprising:

a determination module for determining a security level used by the current application;

The extraction module is specifically configured to:

Features corresponding to the security level are extracted in the fingerprint image.
A terminal, comprising: a housing, a processor, a memory, a circuit board, and a power supply circuit, wherein the circuit board is disposed inside the space enclosed by the housing, the processor and the memory are disposed on the circuit board; and the power circuit For powering various circuits or devices of the terminal; the memory is for storing executable program code; the processor is configured to execute a program corresponding to the executable program code by reading executable program code stored in the memory for performing the following step:

Collecting fingerprint images;

Extracting features in the fingerprint image;

Determining, according to the feature, whether the person to be verified is a living body;

If the person to be verified is a living body, fingerprint matching is performed to obtain a fingerprint matching result.
A non-volatile computer storage medium, characterized in that the non-volatile computer storage medium stores one or more modules for performing the following steps:

Collecting fingerprint images;

Extracting features in the fingerprint image;

Determining, according to the feature, whether the person to be verified is a living body;

If the person to be verified is a living body, fingerprint matching is performed to obtain a fingerprint matching result.