Fingerprint identification method and device, terminal equipment and storage medium

Abstract

This application provides a fingerprint recognition method, apparatus, terminal device, and storage medium. The method includes: acquiring a first fingerprint image and a second fingerprint image collected at different times; determining a first pressure value corresponding to the first fingerprint image and a second pressure value corresponding to the second fingerprint image; and determining successful recognition when the first pressure value and the second pressure value satisfy different pressure levels, and both the first and second fingerprint images are obtained from collecting genuine fingerprints. This technical solution eliminates the need for a high-definition optical fingerprint sensor to detect whether a fingerprint image was obtained from a forged fingerprint, reducing costs, avoiding limitations imposed by existing methods such as size and power consumption, improving fingerprint recognition security, and enhancing user experience.

Description

Technical Field

[0001] This application relates to the field of terminal technology, and in particular to a fingerprint recognition method, device, terminal equipment and storage medium. Background Technology

[0002] With the rapid development of network technology, high screen-to-body ratio terminal devices have become an inevitable trend in the development of smart terminals. Currently, fingerprint recognition in high screen-to-body ratio terminal devices typically uses optical under-display fingerprint sensors, ensuring fingerprint recognition functionality while increasing the screen-to-body ratio.

[0003] In existing technologies, fake fingerprint films made of certain materials are very similar to users' real fingerprint films, which may lead to misidentification. To address this, high-resolution fingerprint images can be acquired, and the sweat pores and sweat information in the high-resolution fingerprint images can be used to determine whether the acquired fingerprint image comes from a real fingerprint.

[0004] However, high-resolution fingerprint images require the use of high-definition optical fingerprint sensors, which are not only costly but also occupy a large area and consume a lot of power. They are not suitable for portable mobile terminals with limitations in size and power consumption, and still pose security risks. Summary of the Invention

[0005] This application provides a fingerprint recognition method, device, terminal equipment, and storage medium to address the problems of high cost, high power consumption, and existing security risks in existing fingerprint recognition anti-counterfeiting solutions.

[0006] The first aspect of this application provides a fingerprint recognition method, including:

[0007] Acquire first and second fingerprint images captured at different times;

[0008] Determine the first pressure value corresponding to the first fingerprint image and the second pressure value corresponding to the second fingerprint image;

[0009] When the first pressure value and the second pressure value meet different pressure levels, and both the first fingerprint image and the second fingerprint image are obtained from real fingerprints, the recognition is determined to be successful.

[0010] Optionally, the time interval between acquiring the first fingerprint image and the second fingerprint image meets a preset time interval threshold.

[0011] In one possible design of the first aspect, acquiring the first fingerprint image and the second fingerprint image collected at different times includes:

[0012] The system collects multiple fingerprint images when a user presses the fingerprint sensor once, with each fingerprint image carrying its own collection time and collection pressure value.

[0013] Based on the acquisition time and acquisition pressure value carried in each fingerprint image frame, the first fingerprint image and the second fingerprint image are obtained from the multiple fingerprint images.

[0014] In another possible design of the first aspect, acquiring the first fingerprint image and the second fingerprint image collected at different times includes:

[0015] Acquire the first fingerprint image when the user presses the fingerprint sensor;

[0016] Calculate the first pressure value corresponding to the first fingerprint image, and determine the pressure level to which the first pressure value belongs;

[0017] A press instruction is issued based on the pressure level to which the first pressure value belongs, and the press instruction is used to instruct the user to press the fingerprint sensor with a pressure force different from the pressure level to which the first pressure value belongs;

[0018] Acquire the second fingerprint image when the user presses the fingerprint sensor based on the press instruction.

[0019] In another possible design of the first aspect, acquiring the first fingerprint image and the second fingerprint image collected at different times includes:

[0020] The system collects multiple fingerprint images from a single press of the fingerprint sensor by the user, with each fingerprint image carrying its own acquisition time.

[0021] Calculate the pressure value corresponding to each frame of the fingerprint image;

[0022] Based on the pressure value corresponding to each frame of fingerprint image, the first fingerprint image and the second fingerprint image with pressure values ​​belonging to different pressure levels are obtained from the multiple frames of fingerprint images.

[0023] In another possible design of the first aspect, for any one of the first fingerprint image and the second fingerprint image, the pressure value corresponding to the fingerprint image is determined, including:

[0024] Determine the effective calculated area of ​​the fingerprint image;

[0025] The pressure value corresponding to the fingerprint image is determined based on the preset correspondence between area and pressure value.

[0026] Optionally, determining the effective calculated area of ​​the fingerprint image includes:

[0027] Determine the imaging area coefficient of the fingerprint image;

[0028] The actual imaging area in the fingerprint image is determined based on the grayscale value of each pixel in the fingerprint image and a preset grayscale threshold.

[0029] The effective calculated area of ​​the fingerprint image is determined based on the imaging area coefficient and the actual imaging area.

[0030] Optionally, determining the imaging area coefficient of the fingerprint image includes:

[0031] The number of imaging pixels in the fingerprint image is counted, where the imaging pixel refers to a pixel whose grayscale value is not white;

[0032] The imaging area coefficient of the fingerprint image is determined based on the number of imaging pixels in the fingerprint image and the theoretical number of pixels included in the fingerprint image.

[0033] Optionally, determining the actual imaging area in the fingerprint image based on the grayscale value of each pixel in the fingerprint image and a preset grayscale threshold includes:

[0034] The effective pixels in the fingerprint image are determined, and the effective pixels are those whose gray values ​​are less than a preset gray value threshold.

[0035] The actual imaging area in the fingerprint image is determined based on the number of valid pixels in the fingerprint image.

[0036] In another possible design of the first aspect, the pressure level includes: a first pressure level less than a first pressure threshold and a second pressure level greater than a second pressure threshold, wherein the second pressure threshold is greater than the first pressure threshold.

[0037] Optionally, the method further includes:

[0038] Determine the pressure level to which the first pressure value belongs;

[0039] When the first pressure value belongs to the first pressure level, determine whether the first fingerprint image is obtained from a real fingerprint.

[0040] When the first fingerprint image is obtained from a real fingerprint, it is determined whether the second pressure value belongs to the second pressure level;

[0041] When the second pressure value belongs to the second pressure level, determine whether the second fingerprint image was obtained from a real fingerprint.

[0042] Optionally, the method further includes:

[0043] Determine the pressure level to which the first pressure value belongs and the pressure level to which the second pressure value belongs;

[0044] Determine whether the first pressure value and the second pressure value belong to different pressure levels;

[0045] When the first pressure value and the second pressure value belong to different pressure levels, determine whether the first fingerprint image and the second fingerprint image are obtained from real fingerprints.

[0046] In another possible design of the first aspect, for any one of the first fingerprint image and the second fingerprint image, determining whether the fingerprint image was obtained from a real fingerprint includes:

[0047] The fingerprint image is input into the fingerprint recognition model to determine whether the fingerprint image was obtained from a real fingerprint. The fingerprint recognition model is a pre-trained model used to identify whether the input fingerprint image was obtained from a real fingerprint.

[0048] A second aspect of this application provides a fingerprint recognition device, comprising: an acquisition module, a processing module, and a determination module;

[0049] The acquisition module is used to acquire the first fingerprint image and the second fingerprint image collected at different times;

[0050] The processing module is used to determine a first pressure value corresponding to the first fingerprint image and a second pressure value corresponding to the second fingerprint image;

[0051] The determining module is used to determine successful recognition when the first pressure value and the second pressure value meet different pressure levels, and when both the first fingerprint image and the second fingerprint image are obtained from real fingerprints.

[0052] Optionally, the time interval between acquiring the first fingerprint image and the second fingerprint image meets a preset time interval threshold.

[0053] In one possible design of the second aspect, the acquisition module has multiple fingerprint images for acquiring a single press of the fingerprint sensor by the user, each fingerprint image carrying its own acquisition time and acquisition pressure value, and acquiring the first fingerprint image and the second fingerprint image from the multiple fingerprint images based on the acquisition time and acquisition pressure value carried by each fingerprint image.

[0054] In another possible design of the second aspect, the acquisition module has the following functions: acquiring a first fingerprint image when a user presses a fingerprint sensor; calculating a first pressure value corresponding to the first fingerprint image; determining the pressure level to which the first pressure value belongs; issuing a press instruction based on the pressure level to which the first pressure value belongs; the press instruction instructing the user to press the fingerprint sensor with a pressure force different from the pressure level to which the first pressure value belongs; and acquiring a second fingerprint image when the user presses the fingerprint sensor based on the press instruction.

[0055] In another possible design of the second aspect, the acquisition module is specifically used to acquire multiple fingerprint images when the user presses the fingerprint sensor once, each fingerprint image carrying its own acquisition time, calculating the pressure value corresponding to each fingerprint image, and based on the pressure value corresponding to each fingerprint image, acquiring the first fingerprint image and the second fingerprint image whose pressure values ​​belong to different pressure levels from the multiple fingerprint images.

[0056] In another possible design of the second aspect, for any one of the first fingerprint image and the second fingerprint image, the processing module is specifically used to determine the effective calculated area of ​​the fingerprint image and determine the pressure value corresponding to the fingerprint image according to a preset correspondence between area and pressure value.

[0057] Optionally, the processing module is specifically used to determine the imaging area coefficient of the fingerprint image, determine the actual imaging area in the fingerprint image based on the grayscale value of each pixel in the fingerprint image and a preset grayscale threshold, and determine the effective calculated area of ​​the fingerprint image based on the imaging area coefficient and the actual imaging area.

[0058] Optionally, the processing module is specifically used to count the number of imaging pixels in the fingerprint image, where the imaging pixel refers to a pixel whose grayscale value is not white, and to determine the imaging area coefficient of the fingerprint image based on the number of imaging pixels in the fingerprint image and the theoretical number of pixels included in the fingerprint image.

[0059] Optionally, the processing module is specifically used to determine the effective pixels in the fingerprint image, wherein the effective pixels refer to pixels whose grayscale value is less than a preset grayscale threshold, and to determine the actual imaging area in the fingerprint image based on the number of effective pixels in the fingerprint image.

[0060] In another possible design of the second aspect, the pressure level includes: a first pressure level less than a first pressure threshold and a second pressure level greater than a second pressure threshold, wherein the second pressure threshold is greater than the first pressure threshold.

[0061] Optionally, the processing module is further configured to determine the pressure level to which the first pressure value belongs, and when the first pressure value belongs to the first pressure level, determine whether the first fingerprint image is obtained by collecting a real fingerprint, when the first fingerprint image is obtained by collecting a real fingerprint, determine whether the second pressure value belongs to the second pressure level, and when the second pressure value belongs to the second pressure level, determine whether the second fingerprint image is obtained by collecting a real fingerprint.

[0062] Optionally, the processing module is further configured to determine the pressure level to which the first pressure value belongs and the pressure level to which the second pressure value belongs, determine whether the first pressure value and the second pressure value belong to different pressure levels, and when the first pressure value and the second pressure value belong to different pressure levels, determine whether the first fingerprint image and the second fingerprint image are obtained from real fingerprints.

[0063] In another possible design of the second aspect, for any one of the first fingerprint image and the second fingerprint image, the processing module is further specifically used to input the fingerprint image into a fingerprint recognition model to determine whether the fingerprint image is obtained from a real fingerprint. The fingerprint recognition model is a pre-trained model used to identify whether the input fingerprint image is obtained from a real fingerprint.

[0064] A third aspect of this application provides a terminal device including a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the methods described in the first aspect and various possible designs of the first aspect.

[0065] A fourth aspect of this application provides a storage medium storing instructions that, when run on a computer, cause the computer to perform the methods described in the first aspect and various possible designs of the first aspect.

[0066] The fifth aspect of this application provides a program product containing instructions that, when run on a computer, cause the computer to perform the methods described in the first aspect and various possible designs of the first aspect.

[0067] A sixth aspect of this application provides a chip including a memory and a processor. The memory stores code and data and is coupled to the processor. The processor executes the code in the memory such that the chip is used to perform the methods described in the first aspect and various possible designs of the first aspect.

[0068] The fingerprint recognition method, apparatus, terminal device, and storage medium provided in this application acquire first and second fingerprint images collected at different times, determine a first pressure value corresponding to the first fingerprint image and a second pressure value corresponding to the second fingerprint image, and determine successful recognition only when the first and second pressure values ​​meet different pressure levels and both the first and second fingerprint images are obtained from real fingerprints. This eliminates the need for a high-definition optical fingerprint sensor to detect whether a fingerprint image was obtained from a forged fingerprint, reducing costs, avoiding existing limitations such as size and power consumption, improving fingerprint recognition security, and enhancing user experience. Attached Figure Description

[0069] Figure 1 A flowchart of Embodiment 1 of the fingerprint recognition method provided in this application;

[0070] Figure 2 A schematic flowchart of Embodiment 2 of the fingerprint recognition method provided in this application;

[0071] Figure 3 This is a schematic diagram showing the changes in pressure value and compression time during a single pressure application.

[0072] Figure 4 A schematic flowchart of Embodiment 3 of the fingerprint recognition method provided in this application;

[0073] Figure 5 A schematic flowchart of Embodiment 4 of the fingerprint recognition method provided in this application;

[0074] Figure 6 A flowchart illustrating Embodiment 5 of the fingerprint recognition method provided in this application;

[0075] Figure 7 This is a schematic diagram of the fingerprint pattern in the first fingerprint image;

[0076] Figure 8 This is a schematic diagram of the ridge pattern in the second fingerprint image;

[0077] Figure 9 A schematic flowchart of Embodiment Six of the fingerprint recognition method provided in this application;

[0078] Figure 10 A flowchart illustrating Embodiment Seven of the fingerprint recognition method provided in this application;

[0079] Figure 11 This is a schematic diagram of the structure of an embodiment of the fingerprint recognition device provided in this application.

[0080] Figure 12This is a schematic diagram of the structure of a terminal device provided in an embodiment of this application. Detailed Implementation

[0081] With the rapid development of network technology, high screen-to-body ratio terminal devices have become an inevitable trend in the development of smart terminals. However, high screen-to-body ratios bring some problems, including how to configure fingerprint recognition sensors. Currently, most terminal devices that support fingerprint recognition use optical under-display fingerprint sensors.

[0082] Specifically, in terminal devices, optical-based under-display fingerprint sensors are placed inside the display screen of the terminal device. When the terminal device collects the user's fingerprint information, the display screen of the terminal device emits light, and the light is reflected by the display screen onto the fingerprint sensor to form an image, thus obtaining a fingerprint image.

[0083] However, fake fingerprint films can be divided into 2D and 3D fingerprint films. 2D fake fingerprint films refer to fake fingerprints that are all on a single plane, meaning the fake fingerprint itself is an image, such as a fingerprint image on an A4 sheet of paper. 3D fake fingerprint films, on the other hand, refer to fake fingerprints that are not on a single plane and have a 3D structure like real fingerprints, such as fake fingerprint films made of silicone. Because criminals can easily collect users' fingerprints and quickly create fake fingerprint films to unlock users' devices, this can lead to financial losses and the leakage of sensitive information. In other words, fake fingerprint films made of certain materials are very similar to users' real fingerprints. For example, experiments have verified that fake fingerprint films made from common materials such as red inkpads, A4 paper, and tape can be used to unlock devices. Obtaining someone's fingerprint in daily life is very easy, which poses a significant security risk to under-display optical fingerprint scanners, potentially leading to unauthorized unlocking of devices by malicious users.

[0084] To address this issue, existing optical fingerprint anti-counterfeiting solutions all rely on judging a single image. For example, a high-resolution optical fingerprint sensor is used to collect a fingerprint, and the information about sweat pores and sweat in the high-resolution fingerprint image is analyzed to determine whether the fingerprint image was obtained from a real fingerprint. If the fingerprint image contains information about sweat pores and sweat, it is determined that the fingerprint image was obtained from a real fingerprint; if the fingerprint image does not contain information about sweat pores and sweat, it is determined that the fingerprint image was not obtained from a real fingerprint. However, this solution requires high image resolution, necessitating the use of a high-resolution optical fingerprint sensor. Furthermore, due to the size limitations of terminal devices, high-resolution optical fingerprint sensors are not suitable for use in small terminal devices such as mobile phones and tablets.

[0085] For example, existing technologies can train a deep learning model based on a convolutional neural network using collected real and fake fingerprint images to determine whether the collected fingerprint image was obtained from a real fingerprint. However, because some fake fingerprints made of certain materials can be very similar to real fingerprint images when a single image is collected, they are difficult to distinguish, resulting in a lack of security.

[0086] In addition, traditional capacitive fingerprint recognition solutions can also employ fingerprint anti-counterfeiting schemes based on blood and heart rate signals. This requires the addition of a dedicated sensor to collect blood and heart rate signals. When recognizing a fingerprint, the system determines whether the fingerprint is genuine by judging whether blood flow and heart rate signals can be detected. However, for under-display fingerprint recognition scenarios, adding sensors to collect blood flow and heart rate signals presents significant technical challenges and increases costs considerably, making widespread application impractical.

[0087] Furthermore, in existing technologies, especially for small portable terminal devices such as mobile phones, there are many challenges to implementing fingerprint anti-counterfeiting solutions. These challenges include the fact that the collected fingerprint image is a partial image rather than the entire fingerprint, as well as limitations in model storage space, computing resources, and computing time.

[0088] This application addresses the security vulnerabilities of existing fingerprint recognition schemes by proposing a fingerprint recognition method. This method acquires first and second fingerprint images collected at different times, determines a first pressure value corresponding to the first fingerprint image and a second pressure value corresponding to the second fingerprint image. Successful recognition is confirmed only when the first and second pressure values ​​meet different pressure levels and both the first and second fingerprint images are obtained from genuine fingerprints. This method eliminates the need for high-definition optical fingerprint sensors to detect whether a fingerprint image was obtained from a forged fingerprint, reducing costs, avoiding limitations in size and power consumption, improving fingerprint recognition security, and enhancing user experience.

[0089] It is understood that the execution subject of the embodiments of this application can be a terminal device with fingerprint recognition function, such as a mobile phone, tablet computer, attendance terminal, fingerprint door lock or other device with optical fingerprint sensor. The embodiments of this application do not limit the terminal device to which it is applicable, and it can be determined according to the actual situation.

[0090] The technical solution of this application will be described in detail below through specific embodiments. It should be noted that the following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will be described below with reference to the accompanying drawings.

[0091] In this embodiment of the application, "multiple" refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone. The character " / " generally indicates that the preceding and following related objects have an "or" relationship.

[0092] Figure 1 This is a flowchart of an embodiment of the fingerprint recognition method provided in this application. Figure 1 As shown, the fingerprint recognition method provided in this application embodiment may include the following steps:

[0093] Step 11: Obtain the first and second fingerprint images captured at different times.

[0094] In the embodiments of this application, the terminal device has an optical fingerprint sensor. When a user has an identification request, the user sends an identification request by pressing the optical fingerprint sensor on the terminal device. In this way, the terminal device obtains the fingerprint image to be identified based on the user's identification request.

[0095] For example, the optical fingerprint sensor in this embodiment is an under-display optical fingerprint module, which is used to collect fingerprint images and may have the characteristic of collecting multiple frames of fingerprint images in a short period of time.

[0096] In practical applications, all types of fake fingerprints can exhibit characteristics different from live fingerprints under varying pressure. Live fingerprints correspond to different fingerprint images under different pressure levels, while the fingerprint image of a 2D fake fingerprint remains essentially unchanged with changes in pressure. Furthermore, the fingerprint image of a 3D fake fingerprint shows different effects from a live fingerprint under different pressure levels. Therefore, in the embodiments of this application, based on the aforementioned characteristics of fake and live fingerprints, when a user presses the optical fingerprint sensor of a terminal device, the optical fingerprint sensor can acquire multiple fingerprint images at different times, thereby enabling the terminal device to obtain a first fingerprint image and a second fingerprint image acquired at different times.

[0097] It is worth noting that, in the embodiments of this application, the time interval between the acquisition of the first fingerprint image and the second fingerprint image meets a preset time interval threshold.

[0098] Specifically, each fingerprint image acquired by the optical fingerprint sensor corresponds to a acquisition time. Therefore, in this embodiment, in order to ensure that the two fingerprint images obtained by the terminal device are obtained from real fingerprints, the acquisition time interval between the first fingerprint image and the second fingerprint image meets a preset time interval threshold.

[0099] For example, the acquisition time of the first fingerprint image and the second fingerprint image cannot exceed a preset time interval threshold, so as to ensure the security of fingerprint recognition by the terminal device.

[0100] Step 12: Determine the first pressure value corresponding to the first fingerprint image and the second pressure value corresponding to the second fingerprint image.

[0101] Because users' fingerprints have different patterns, the ridge area of ​​fingerprint images varies depending on the pressure applied; the greater the pressure, the larger the area occupied by the ridges. Therefore, in this embodiment, by analyzing the actual calculated areas of the first and second fingerprint images, the first pressure value corresponding to the first fingerprint image and the second pressure value corresponding to the second fingerprint image can be determined.

[0102] For an explanation of the implementation principle of this step, please refer to the following: Figure 6 The descriptions in the illustrated embodiments will not be repeated here.

[0103] Step 13: When the first pressure value and the second pressure value meet different pressure levels, and both the first fingerprint image and the second fingerprint image are obtained from real fingerprints, the recognition is confirmed to be successful.

[0104] The pressure levels include: a first pressure level less than a first pressure threshold and a second pressure level greater than a second pressure threshold, wherein the second pressure threshold is greater than the first pressure threshold.

[0105] In practical applications, existing optical under-display fingerprint recognition solutions on terminal devices are easily compromised by criminals using cheap materials to create fake fingerprint films, posing a significant security risk to consumers. To address this, this application's embodiments utilize first and second fingerprint images acquired under different pressure levels. By determining whether the pressure values ​​corresponding to the first and second fingerprint images meet different pressure levels, it ensures that users can press the fingerprint sensor at different pressure levels. Furthermore, by determining that both the first and second fingerprint images are obtained from real fingerprints, it ensures that the acquired fingerprint images originate from a living person.

[0106] Specifically, the terminal device collects the first and second fingerprint images of the user's fingerprint at different times and under different pressure levels. First, it determines whether the obtained first and second fingerprint images match the pressure level. Then, it determines whether the first and second fingerprint images under different pressure levels are both obtained from the collected real fingerprint. Only if both are obtained from the collected real fingerprint is it determined that the user who issued the identification request is a legitimate user.

[0107] The fingerprint recognition method provided in this application acquires a first fingerprint image and a second fingerprint image collected at different times, determines a first pressure value corresponding to the first fingerprint image and a second pressure value corresponding to the second fingerprint image, and determines successful recognition only when the first pressure value and the second pressure value meet different pressure levels and both the first fingerprint image and the second fingerprint image are obtained from real fingerprints. It can detect whether the acquired fingerprint image is obtained from a forged fingerprint without using a high-definition optical fingerprint sensor to collect fingerprints, reducing costs, avoiding existing limitations such as size and power consumption, improving fingerprint recognition security, and enhancing user experience.

[0108] For example, in one possible design of an embodiment of this application, Figure 2 This is a flowchart illustrating a second embodiment of the fingerprint recognition method provided in this application. Figure 2 As shown, in the embodiments of this application, step 11 above can be implemented through the following steps:

[0109] Step 21: Collect multiple fingerprint images when the user presses the fingerprint sensor once. Each fingerprint image carries its own collection time and collection pressure value.

[0110] For example, in an embodiment of this application, a certain type of terminal device has a pressure fingerprint sensor that can record the changing trend of pressure value and pressing time during a single pressure process, and acquire multiple frames of fingerprint images, wherein each frame of fingerprint image carries its own acquisition time and acquisition pressure value.

[0111] For example, Figure 3 This is a diagram illustrating the changes in pressure value and compression time during a single compression. For example... Figure 3 As shown, the pressure fingerprint sensor can capture multiple frames of fingerprint images during a single press by the user. For example, refer to... Figure 3 As shown, five fingerprint images can be acquired in a single pressure process, with each fingerprint image carrying the acquisition time and acquisition pressure value.

[0112] Step 22: Based on the acquisition time and acquisition pressure value carried in each fingerprint image frame, obtain the first fingerprint image and the second fingerprint image from multiple fingerprint images.

[0113] In this embodiment, after the terminal device acquires multiple fingerprint images, it can select two fingerprint images that meet the pressure conditions based on the acquisition time and acquisition pressure value carried in each fingerprint image.

[0114] Specifically, the terminal device first selects a fingerprint image from multiple fingerprint images whose pressure value meets the first pressure level based on the acquisition time and acquisition pressure value carried by each fingerprint image. Then, it calculates the pressure value corresponding to the fingerprint image based on the gray value of each pixel in the fingerprint image and the size and area of ​​the fingerprint image, and determines whether the pressure value corresponding to the fingerprint image meets the first pressure level. If so, the fingerprint image is determined to be the first fingerprint image.

[0115] Similarly, based on the acquisition time and acquisition pressure value carried by each fingerprint image frame, a fingerprint image frame whose pressure value meets the second pressure level is selected from multiple fingerprint images. Then, the pressure value corresponding to the fingerprint image is calculated, and it is determined whether the pressure value corresponding to the fingerprint image meets the second pressure level. If so, the fingerprint image is determined to be the second fingerprint image.

[0116] Furthermore, in order to ensure the security of fingerprint recognition on the terminal device, the time interval between the acquisition of the first fingerprint image and the second fingerprint image needs to meet a preset time interval threshold.

[0117] Specifically, the acquisition time interval between the first fingerprint image and the second fingerprint image is calculated based on the acquisition time of the first fingerprint image and the acquisition time of the second fingerprint image. Then, it is determined whether the acquisition time interval is less than a preset time interval threshold. If so, it is determined that the first fingerprint image and the second fingerprint image meet the requirements.

[0118] The fingerprint recognition method provided in this application acquires multiple frames of fingerprint images when a user presses the fingerprint sensor once. Each frame of the fingerprint image carries its own acquisition time and acquisition pressure value. Based on the acquisition time and acquisition pressure value carried in each frame of the fingerprint image, a first fingerprint image and a second fingerprint image are obtained from the multiple frames of fingerprint images. That is, the first and second fingerprint images that meet the requirements can be determined by the user's single press, without the need for additional sensors. Fingerprint image acquisition can be achieved using only the existing fingerprint sensor, saving costs and avoiding the technical difficulties of adding a fingerprint sensor under the display screen. It can more effectively detect 2D and 3D fake fingerprint films, increasing recognition security. In addition, no additional operation is required from the user; normal fingerprint verification is all that is needed, improving the user experience.

[0119] For example, in another possible design of an embodiment of this application, Figure 4 This is a flowchart illustrating Embodiment 3 of the fingerprint recognition method provided in this application. Figure 4 As shown, in the embodiments of this application, step 11 above can be implemented through the following steps:

[0120] Step 41: Obtain the first fingerprint image when the user presses the fingerprint sensor.

[0121] For example, in this embodiment, the fingerprint sensor of some terminal devices can only collect one fingerprint image during a single press by the user. Therefore, if two fingerprint images with different pressing pressure are to be obtained, the user needs to perform two pressing processes.

[0122] Specifically, the terminal device uses a fingerprint sensor to acquire a first fingerprint image of the user during a single press. Optionally, the terminal device also records the acquisition time of the first fingerprint image so that when the second fingerprint image is acquired, the terminal device can use the acquisition time of the first fingerprint image and the acquisition time of the second fingerprint image to determine whether the acquisition time of the two fingerprint images meets the time requirement.

[0123] Step 42: Calculate the first pressure value corresponding to the first fingerprint image and determine the pressure level to which the first pressure value belongs.

[0124] Optionally, after the terminal device obtains the first fingerprint image, it first obtains the grayscale value of each pixel in the first fingerprint image, and determines the first pressure value based on the grayscale values ​​of all pixels in the first fingerprint image.

[0125] For example, in this embodiment, the terminal device is pre-set with a first pressure level and a second pressure level. Pressure values ​​with a pressure value less than the first pressure threshold belong to the first pressure level, and pressure values ​​with a pressure value greater than the second pressure threshold belong to the second pressure level. Furthermore, the second pressure threshold is greater than the first pressure threshold.

[0126] In this embodiment, the pressure level to which the first pressure value belongs is determined by comparing the first pressure value with the first pressure threshold and the second pressure threshold. That is, if the first pressure value is less than or equal to the first pressure threshold, the first pressure value is determined to belong to the first pressure level; if the first pressure value is greater than or equal to the second pressure threshold, the first pressure value is determined to belong to the second pressure level; if the first pressure value is between the first pressure threshold and the second pressure threshold, the first pressure value is determined to not meet the pressure requirements and is discarded.

[0127] Step 43: Issue a press instruction based on the pressure level to which the first pressure value belongs, the press instruction being used to instruct the user to press the fingerprint sensor with a pressure force different from the pressure level to which the first pressure value belongs.

[0128] In this embodiment, in order to obtain two fingerprint images that meet different pressure levels, after determining the pressure level to which the first pressure value corresponding to the first fingerprint image belongs, a pressure instruction can be issued to instruct the user to press the fingerprint sensor with a pressure different from the first pressure value, thereby obtaining a second fingerprint image with a pressure level that meets the requirements.

[0129] For example, in this embodiment, the terminal device can issue a pressing instruction via voice. For instance, when it is determined that the first pressure value belongs to the first pressure level, it can issue "Please press with heavy force"; when it is determined that the first pressure value belongs to the second pressure level, it can issue "Please press with light force".

[0130] Optionally, the terminal device can also issue pressing prompts via text, such as displaying "Please press with heavy force" or "Please press with light force" on the user interface to prompt the user to press with the appropriate force.

[0131] Step 44: Obtain a second fingerprint image when the user presses the fingerprint sensor based on the press instruction.

[0132] In this embodiment, after the user receives the pressing instruction from the terminal device, the user can press the fingerprint sensor according to the pressing instruction, so that the terminal device can obtain the second fingerprint image collected by the fingerprint sensor.

[0133] It is worth noting that after obtaining the second fingerprint image, the terminal device also needs to determine the second pressure value corresponding to the second fingerprint image based on the grayscale value of each pixel in the second fingerprint image, and then determine whether the second pressure value and the first pressure value belong to different pressure levels. If so, it is determined that the obtained second fingerprint image meets the pressure requirements; otherwise, it is determined that the obtained second fingerprint image does not meet the pressure requirements, and the second fingerprint image needs to be obtained again.

[0134] Furthermore, to ensure the security of fingerprint recognition on the terminal device, this embodiment also needs to determine that the acquisition time interval between the first and second fingerprint images meets a preset time interval threshold. The implementation scheme for this determination can be found in the description of the above embodiments, and will not be repeated here.

[0135] The fingerprint recognition method provided in this application acquires a first fingerprint image when a user presses a fingerprint sensor, calculates a first pressure value corresponding to the first fingerprint image, determines the pressure level to which the first pressure value belongs, and issues a press instruction based on the pressure level to which the first pressure value belongs. This press instruction instructs the user to press the fingerprint sensor with a pressure force different from the pressure level to which the first pressure value belongs. Finally, a second fingerprint image is acquired when the user presses the fingerprint sensor based on the press instruction. This technical solution does not require limiting the function of the fingerprint sensor; it only requires the user to perform two press processes based on the press prompt, making the solution simple and easy to implement.

[0136] For example, in another possible design of an embodiment of this application, Figure 5 This is a flowchart illustrating Embodiment 4 of the fingerprint recognition method provided in this application. Figure 5As shown, in the embodiments of this application, step 11 above can be implemented through the following steps:

[0137] Step 51: Collect multiple fingerprint images when the user presses the fingerprint sensor once, with each fingerprint image carrying its own collection time.

[0138] Optionally, for some fingerprint sensors that only have the ability to acquire multiple frames of fingerprint images, they can acquire multiple frames of fingerprint images during a single press by the user. However, since they do not have a pressure detection function, in this embodiment, the terminal device acquires multiple frames of fingerprint images through the fingerprint sensor, wherein each frame of fingerprint image can carry its own acquisition time.

[0139] Step 52: Calculate the pressure value corresponding to each frame of fingerprint image.

[0140] Optionally, in this embodiment, the pressure value corresponding to each frame of the fingerprint image can be calculated using a certain pressure detection method. For example, the corresponding pressure value can be determined by the grayscale value of each pixel in each frame of the fingerprint image.

[0141] For an explanation of the implementation principle of this step, please refer to the following: Figure 6 The description of the illustrated embodiment will not be repeated here.

[0142] Step 53: Based on the pressure value corresponding to each fingerprint image frame, obtain the first fingerprint image and the second fingerprint image from multiple fingerprint images, whose pressure values ​​belong to different pressure levels.

[0143] In this embodiment, after the terminal device obtains the pressure value corresponding to each frame of fingerprint image, it can directly obtain two fingerprint images belonging to different pressure levels from multiple frames of fingerprint images based on the pressure value of each frame of fingerprint image. For example, the first pressure value corresponding to the first fingerprint image belongs to the first pressure level, and the pressure value corresponding to the second fingerprint image belongs to the second pressure level; or, the first pressure value corresponding to the first fingerprint image belongs to the second pressure level, and the pressure value corresponding to the second fingerprint image belongs to the first pressure level.

[0144] The fingerprint recognition method provided in this application acquires multiple fingerprint images from a single press of the fingerprint sensor by the user. Each fingerprint image carries its own acquisition time. The pressure value corresponding to each fingerprint image is calculated. Based on the pressure value corresponding to each fingerprint image, first and second fingerprint images belonging to different pressure levels are obtained from the multiple fingerprint images. In this technical solution, multiple images can be acquired through a single press by the user, and then the first and second fingerprint images that meet the requirements are determined by calculating the pressure value of each fingerprint image, making the solution simple.

[0145] For example, based on any of the above embodiments, Figure 6 This is a flowchart illustrating Embodiment 5 of the fingerprint recognition method provided in this application. Figure 6 As shown in the embodiments of this application, for any one of the first fingerprint image and the second fingerprint image, determining the pressure value corresponding to the fingerprint image can be achieved through the following steps:

[0146] Step 61: Determine the effective computational area of ​​the fingerprint image.

[0147] In this embodiment, the fingerprint image is a grayscale image, and each pixel in the fingerprint image can be represented by a grayscale value, where the grayscale value of black is 0 and the grayscale value of white is 255. Therefore, the grayscale value of each pixel in the fingerprint image can be represented by a value in the grayscale value range [0, 255], where the larger the grayscale value, the whiter the pixel's grayscale value.

[0148] For example, for a fingerprint image img[h, w] with image height h and image width w, the gray value range of the pixel at position (i, j) is [0, 255], where 0≤i≤h-1 and 0≤j≤w-1.

[0149] In this embodiment, to calculate the pressure value corresponding to each fingerprint image, the imaging area coefficient of the fingerprint image is first determined. Then, based on the gray value of each pixel in the fingerprint image and the preset gray value threshold, the actual imaging area in the fingerprint image is determined. Finally, based on the imaging area coefficient and the actual imaging area, the effective calculation area of ​​the fingerprint image is determined.

[0150] For example, in this embodiment, determining the imaging area coefficient of the fingerprint image specifically includes the following steps:

[0151] A1: Count the number of imaging pixels in the fingerprint image. The imaging pixel refers to the pixel whose grayscale value is not white.

[0152] In this embodiment, since the fingerprint image may include some white unimaged parts, the number of imaging pixels in the fingerprint image can be determined by the grayscale values ​​of black and white.

[0153] Specifically, since the grayscale value of black is 0 and the grayscale value of white is 255, we can determine whether a pixel in the fingerprint image is an imaging pixel based on whether its grayscale value is not 255. Specifically, if the grayscale value of the pixel at position img(i,j) is 255, then that pixel is not an imaging pixel.

[0154] For example, the following formula uses Q(x) to represent whether the pixel at position img(i,j) is imaged:

[0155]

[0156] Correspondingly, the number of imaging pixels in the fingerprint image img[h, w] can be represented as:

[0157] A2: Determine the imaging area coefficient of the fingerprint image based on the number of imaging pixels in the fingerprint image and the theoretical number of pixels included in the fingerprint image.

[0158] For example, in this embodiment, for a fingerprint image img[h, w] with image height h and image width w, the theoretical number of pixels (i.e., theoretical area) it includes is h*w. Therefore, the imaging area coefficient k of the fingerprint image img[h, w] can be expressed by the following formula:

[0159]

[0160] For example, in this embodiment, determining the actual imaging area in the fingerprint image based on the grayscale value of each pixel and a preset grayscale threshold can be achieved through the following steps:

[0161] B1: Identify the valid pixels in the fingerprint image. The valid pixels are those whose grayscale values ​​are less than the preset grayscale threshold.

[0162] In this embodiment, the terminal device may be configured with a preset grayscale threshold. After obtaining the grayscale value of each pixel in the fingerprint image, the device determines whether each pixel is a valid pixel by judging the relationship between the grayscale value of each pixel and the preset grayscale threshold.

[0163] For example, when the grayscale value of a pixel in the fingerprint image is less than the preset grayscale threshold t, the pixel is considered a valid pixel. Optionally, P(x) is used below to represent whether the pixel at position img(i,j) is a valid pixel, as shown in the following formula:

[0164]

[0165] B2: Determine the actual imaging area of ​​the fingerprint image based on the number of valid pixels in the fingerprint image.

[0166] In this embodiment, for a fingerprint image img[h, w] with image height h and image width w, the number of effective pixels in the fingerprint image img[h, w], that is, the actual imaging area in the fingerprint image, can be expressed as:

[0167] Accordingly, in the embodiments of this application, the effective calculated area of ​​the fingerprint image can be determined based on the imaging area coefficient and the actual imaging area calculated above.

[0168] Specifically, the effective computational area A of a fingerprint image can be expressed by the following formula:

[0169]

[0170] It is worth noting that the effective calculated area of ​​the fingerprint image can be obtained from the pressure values ​​of both the first and second fingerprint images using the aforementioned calculation method. The effective area of ​​the fingerprint image varies depending on the pressure applied.

[0171] For example, Figure 7 This is a schematic diagram of the fingerprint pattern in the first fingerprint image. Figure 8 This is a schematic diagram of the ridge pattern of the second fingerprint image. The first pressure value corresponding to the first fingerprint image belongs to the first pressure level, and the second pressure value corresponding to the second fingerprint image belongs to the second pressure level. For example, as shown... Figure 7 and Figure 8 As shown, when the preset grayscale threshold t is equal to 100, the effective calculated area of ​​the first fingerprint image obtained by the implementation method of step 51 is 4516, and the effective calculated area of ​​the second fingerprint image is 5426.

[0172] Step 62: Determine the pressure value corresponding to the fingerprint image based on the preset correspondence between area and pressure value.

[0173] In this embodiment, the terminal device has a pre-stored correspondence between area and pressure value. Therefore, after the terminal device obtains the effective calculated area of ​​the fingerprint image, it can determine the pressure value corresponding to the effective calculated area by querying the pre-set correspondence between area and pressure value, that is, the pressure value corresponding to the fingerprint image.

[0174] For example, the pressure value corresponding to the first fingerprint image can be determined based on the effective calculated area in the first fingerprint image and the preset correspondence between area and pressure value. Similarly, the pressure value corresponding to the second fingerprint image can be determined based on the effective calculated area in the second fingerprint image and the preset correspondence between area and pressure value.

[0175] The fingerprint recognition method provided in this application determines the imaging area coefficient of the fingerprint image by counting the number of imaging pixels in the fingerprint image (pixels whose grayscale value is not white) and the theoretical number of pixels included in the fingerprint image. It then identifies the effective pixels in the fingerprint image (pixels whose grayscale value is less than a preset grayscale threshold) and determines the actual imaging area of ​​the fingerprint image based on the number of effective pixels. Finally, it determines the effective calculated area of ​​the fingerprint image based on the imaging area coefficient and the actual imaging area. Finally, it determines the pressure value corresponding to the fingerprint image based on a preset correspondence between area and pressure value. This technical solution can calculate the corresponding pressure value range based on the fingerprint image itself, resulting in accurate pressure values ​​and laying the foundation for correct fingerprint recognition.

[0176] As an example, based on the above embodiments, Figure 9 This is a flowchart illustrating Embodiment Six of the fingerprint recognition method provided in this application. Figure 9 As shown in the embodiments of this application, the method may further include the following steps:

[0177] Step 91: Determine the pressure level to which the first pressure value belongs.

[0178] Optionally, in an embodiment of this application, after obtaining the first pressure value corresponding to the first fingerprint image, the relationship between the first pressure value and the first pressure threshold and the second pressure threshold is determined.

[0179] For example, if the first pressure value is less than or equal to the first pressure threshold, then the first pressure value corresponding to the first fingerprint image is determined to belong to the first pressure level; if the first pressure value is greater than or equal to the second pressure threshold, then the first pressure value corresponding to the first fingerprint image is determined to belong to the second pressure level. If the first pressure value is greater than the first pressure threshold and less than the second pressure threshold, then the first fingerprint image is determined to not meet the acquisition requirements and is discarded.

[0180] Step 92: When the first pressure value belongs to the first pressure level, determine whether the first fingerprint image is obtained from a real fingerprint.

[0181] Optionally, as an example, if the first pressure value belongs to the first pressure level, it is possible to first detect whether the first fingerprint image was obtained from a real fingerprint, and then determine whether to judge the pressure level to which the second pressure value belongs based on the detection result of the first fingerprint image.

[0182] Step 93: When the first fingerprint image is obtained from a real fingerprint, determine whether the second pressure value belongs to the second pressure level.

[0183] For example, in this embodiment, when the first fingerprint image is obtained from a real fingerprint, it can be determined whether the second pressure value belongs to the second pressure level. However, when the first fingerprint image is not obtained from a real fingerprint, the first fingerprint image can be directly discarded, and the fingerprint recognition can be determined to have failed.

[0184] Step 94: When the second pressure value belongs to the second pressure level, determine whether the second fingerprint image is obtained from a real fingerprint.

[0185] In this embodiment, when the first fingerprint image is obtained from a real fingerprint and the second pressure value belongs to the second pressure level, the system further determines whether the second fingerprint image is obtained from a real fingerprint, and then determines whether the recognition is successful based on the determination result of the second fingerprint image.

[0186] The fingerprint recognition method provided in this application determines the pressure level to which a first pressure value belongs. If the first pressure value belongs to the first pressure level, it determines whether the first fingerprint image was obtained from a real fingerprint. If the first fingerprint image was obtained from a real fingerprint, it determines whether the second pressure value belongs to the second pressure level. If the second pressure value belongs to the second pressure level, it further determines whether the second fingerprint image was obtained from a real fingerprint. In this technical solution, after determining the pressure value and whether the fingerprint is from a real or fake fingerprint, the second fingerprint image is only determined after the first fingerprint image is successfully recognized. This method is simple to implement, easy to implement, and improves recognition efficiency and security.

[0187] As another example, based on the above embodiments, Figure 10 This is a flowchart illustrating Embodiment Seven of the fingerprint recognition method provided in this application. Figure 10 As shown in the embodiments of this application, the method may further include the following steps:

[0188] Step 101: Determine the pressure level to which the first pressure value belongs and the pressure level to which the second pressure value belongs.

[0189] In the embodiments of this application, after the terminal device acquires two fingerprint images, such as a first fingerprint image and a second fingerprint image, it determines the first pressure value corresponding to the first fingerprint image and the second pressure value corresponding to the second fingerprint image, and determines the relationship between the first pressure value and the first pressure threshold and the second pressure threshold, as well as the relationship between the second pressure value and the first pressure threshold and the second pressure threshold, thereby determining the pressure level to which the first pressure value belongs and the pressure level to which the second pressure value belongs.

[0190] Step 102: Determine whether the first pressure value and the second pressure value belong to different pressure levels.

[0191] For example, if the first pressure value is less than or equal to the first pressure threshold and the second pressure value is greater than or equal to the second pressure threshold, or if the first pressure value is greater than or equal to the second pressure threshold and the second pressure value is less than or equal to the first pressure threshold, then it is determined that the first pressure value corresponding to the first fingerprint image and the second pressure value corresponding to the second fingerprint image belong to different pressure levels; otherwise, it is determined that the first fingerprint image and / or the second fingerprint image do not meet the image acquisition requirements, and they are discarded, and fingerprint image acquisition is performed again.

[0192] Step 103: When the first pressure value and the second pressure value belong to different pressure levels, determine whether the first fingerprint image and the second fingerprint image are obtained from real fingerprints.

[0193] As an example, when it is determined from step 102 that the first pressure value and the second pressure value belong to different pressure levels, it is then determined whether the first fingerprint image and the second fingerprint image are obtained from real fingerprints, and then the recognition is determined based on the judgment result of the first fingerprint image and the second fingerprint image.

[0194] It is understandable that recognition is only considered successful if both the first and second fingerprint images are obtained from real fingerprints; otherwise, recognition is considered a failure.

[0195] The fingerprint recognition method provided in this application determines the pressure level of a first pressure value and the pressure level of a second pressure value, and then determines whether the first and second pressure values ​​belong to different pressure levels. If the first and second pressure values ​​belong to different pressure levels, it further determines whether the first and second fingerprint images were obtained from real fingerprints. In this technical solution, the pressure values ​​of the two acquired fingerprint images are first judged. If both meet the pressure requirements, then the real / fake fingerprint judgment is performed. This implementation method is easy to implement and can also ensure recognition efficiency and security.

[0196] For example, in Figure 9 and Figure 10 Based on the illustrated embodiment, for any fingerprint image in the first fingerprint image and the second fingerprint image, determining whether the fingerprint image was obtained from a real fingerprint can be achieved through the following steps:

[0197] The fingerprint image is input into the fingerprint recognition model to determine whether the fingerprint image was obtained from a real fingerprint. The fingerprint recognition model is a pre-trained model used to identify whether the input fingerprint image was obtained from a real fingerprint.

[0198] Specifically, in this embodiment, for the first fingerprint image, the first fingerprint image is input into the fingerprint recognition model to determine whether the first fingerprint image was obtained from a real fingerprint. Similarly, for the second fingerprint image, the second fingerprint image is input into the fingerprint recognition model to determine whether the second fingerprint image was obtained from a real fingerprint. This method can detect whether the input fingerprint image comes from a live fingerprint.

[0199] In this embodiment, the terminal device first collects multiple genuine fingerprint images obtained from collecting real fingerprints and fake fingerprint images obtained from collecting fake fingerprints. Based on these genuine and fake fingerprint images and a convolutional neural network, a deep learning model is trained to obtain a trained fingerprint recognition model. In use, the fingerprint image to be judged is input into the fingerprint recognition model, and the judgment result is determined based on the output of the fingerprint recognition model.

[0200] It is worth noting that in practical applications, the terminal device can first acquire a first fingerprint image when the user presses their finger with a first pressure level (e.g., light pressure), and determine whether the obtained first fingerprint image meets the requirements of the first pressure level. If the obtained first fingerprint image meets the requirements of the first pressure level, it is determined whether the first fingerprint image was obtained from a real fingerprint. If it is determined that the first fingerprint image was obtained from a real fingerprint, then a second fingerprint image is acquired when the user presses their finger with a second pressure level (e.g., heavy pressure), and it is determined whether the obtained second fingerprint image meets the requirements of the second pressure level. If it does, it is determined whether the second fingerprint image was obtained from a real fingerprint. Only when it is determined that both the first and second fingerprint images meet the pressure level requirements and both were obtained from real fingerprints is the recognition considered successful, thereby ensuring the security of fingerprint recognition.

[0201] In this embodiment, when determining whether the first fingerprint image meets the requirement of the first pressure intensity, and when determining whether the second fingerprint image meets the requirement of the second pressure intensity, it is necessary to follow the above... Figure 6 The steps in the illustrated embodiment obtain the pressure value corresponding to the fingerprint image from the fingerprint image itself. This method can prevent criminals from using a substandard fake fingerprint to deceive the system for fingerprint recognition.

[0202] Optionally, determining whether the first fingerprint image and the second fingerprint image were obtained from a real fingerprint can be achieved by inputting the fingerprint image into a real / fake fingerprint identification model based on a convolutional neural network, which then determines whether the fingerprint was obtained from a real fingerprint. It is understood that this real / fake fingerprint identification model is a model pre-trained on historical fingerprint images used to identify whether the input fingerprint image was obtained from a real fingerprint.

[0203] Furthermore, in the embodiments of this application, by ensuring that the fingerprint images carry the acquisition time when acquiring the first fingerprint image and the second fingerprint image, and by ensuring that the time interval between the acquisition times of the first fingerprint image and the second fingerprint image is less than a preset time interval threshold, the security of fingerprint recognition of the terminal device is guaranteed.

[0204] Figure 11 This is a schematic diagram illustrating the structure of an embodiment of the fingerprint recognition device provided in this application. The device can be integrated into a terminal device or implemented through a terminal device. Figure 11 As shown, the device may include: an acquisition module 111, a processing module 112, and a determination module 113.

[0205] The acquisition module 111 is used to acquire the first fingerprint image and the second fingerprint image collected at different times;

[0206] The processing module 112 is used to determine the first pressure value corresponding to the first fingerprint image and the second pressure value corresponding to the second fingerprint image;

[0207] The determining module 113 is used to determine successful recognition when the first pressure value and the second pressure value meet different pressure levels, and when both the first fingerprint image and the second fingerprint image are obtained from real fingerprints.

[0208] For example, in this embodiment, the time interval between the acquisition of the first fingerprint image and the second fingerprint image meets a preset time interval threshold.

[0209] For example, in one possible design of this embodiment, the acquisition module 111 has multiple fingerprint images for acquiring a single fingerprint sensor press by a user. Each fingerprint image carries its own acquisition time and acquisition pressure value. Based on the acquisition time and acquisition pressure value carried by each fingerprint image, the first fingerprint image and the second fingerprint image are acquired from the multiple fingerprint images.

[0210] For example, in another possible design of this embodiment, the acquisition module 111 has the following functions: acquiring the first fingerprint image when a user presses the fingerprint sensor, calculating the first pressure value corresponding to the first fingerprint image, determining the pressure level to which the first pressure value belongs, issuing a press instruction based on the pressure level to which the first pressure value belongs, the press instruction being used to instruct the user to press the fingerprint sensor with a pressure force different from the pressure level to which the first pressure value belongs, and acquiring the second fingerprint image when the user presses the fingerprint sensor based on the press instruction.

[0211] For example, in another possible design of this embodiment, the acquisition module 111 is specifically used to acquire multiple fingerprint images when the user presses the fingerprint sensor once, each fingerprint image carries its own acquisition time, calculate the pressure value corresponding to each fingerprint image, and based on the pressure value corresponding to each fingerprint image, acquire the first fingerprint image and the second fingerprint image whose pressure values ​​belong to different pressure levels from the multiple fingerprint images.

[0212] For example, in any possible design of the embodiments of this application, for any fingerprint image among the first fingerprint image and the second fingerprint image, the processing module 112 is specifically used to determine the effective calculated area of ​​the fingerprint image and determine the pressure value corresponding to the fingerprint image according to the preset correspondence between area and pressure value.

[0213] Optionally, the processing module 112 is specifically used to determine the imaging area coefficient of the fingerprint image, determine the actual imaging area in the fingerprint image based on the gray value of each pixel in the fingerprint image and a preset gray value threshold, and determine the effective calculated area of ​​the fingerprint image based on the imaging area coefficient and the actual imaging area.

[0214] In this embodiment, the processing module 112 is specifically used to count the number of imaging pixels in the fingerprint image, where the imaging pixel refers to a pixel whose grayscale value is not white, and to determine the imaging area coefficient of the fingerprint image based on the number of imaging pixels in the fingerprint image and the theoretical number of pixels included in the fingerprint image.

[0215] In this embodiment, the processing module 112 is specifically used to determine the effective pixels in the fingerprint image. The effective pixels refer to pixels whose grayscale value is less than a preset grayscale threshold. Based on the number of effective pixels in the fingerprint image, the actual imaging area in the fingerprint image is determined.

[0216] For example, in one possible design of this embodiment, the pressure level includes: a first pressure level less than a first pressure threshold and a second pressure level greater than a second pressure threshold, wherein the second pressure threshold is greater than the first pressure threshold.

[0217] As an example, the processing module 112 is further configured to determine the pressure level to which the first pressure value belongs, and when the first pressure value belongs to the first pressure level, determine whether the first fingerprint image is obtained by collecting a real fingerprint, when the first fingerprint image is obtained by collecting a real fingerprint, determine whether the second pressure value belongs to the second pressure level, and when the second pressure value belongs to the second pressure level, determine whether the second fingerprint image is obtained by collecting a real fingerprint.

[0218] As another example, the processing module 112 is also used to determine the pressure level to which the first pressure value belongs and the pressure level to which the second pressure value belongs, to determine whether the first pressure value and the second pressure value belong to different pressure levels, and when the first pressure value and the second pressure value belong to different pressure levels, to determine whether the first fingerprint image and the second fingerprint image are obtained from real fingerprints.

[0219] In any of the above possible designs of the embodiments of this application, for any fingerprint image among the first fingerprint image and the second fingerprint image, the processing module 112 is further specifically used to input the fingerprint image into the fingerprint recognition model to determine whether the fingerprint image is obtained by collecting real fingerprints. The fingerprint recognition model is a pre-trained model used to identify whether the input fingerprint image is obtained by collecting real fingerprints.

[0220] The fingerprint recognition device in this embodiment can be used to perform... Figures 1 to 10 The implementation schemes of the methods shown in the embodiments are similar in specific implementation and technical effect, and will not be described again here.

[0221] It should be noted that the division of the various modules in the above device is merely a logical functional division. In actual implementation, they can be fully or partially integrated into a single physical entity, or they can be physically separated. Furthermore, these modules can be implemented entirely in software via processing element calls; they can be fully implemented in hardware; or some modules can be implemented by processing element calls to software, while others are implemented in hardware. For example, a determination module can be a separate processing element, or it can be integrated into a chip within the above device. Alternatively, it can be stored as program code in the memory of the above device, and its function can be called and executed by a processing element of the device. The implementation of other modules is similar. Moreover, these modules can be fully or partially integrated together, or they can be implemented independently. The processing element mentioned here can be an integrated circuit with signal processing capabilities. In the implementation process, each step of the above method or each of the above modules can be completed through integrated logic circuits in the hardware of the processor element or through software instructions.

[0222] For example, these modules can be one or more integrated circuits configured to implement the above methods, such as one or more application-specific integrated circuits (ASICs), one or more digital signal processors (DSPs), or one or more field-programmable gate arrays (FPGAs). As another example, when a module is implemented using processing element scheduler code, the processing element can be a general-purpose processor, such as a central processing unit (CPU) or other processor capable of calling program code. Furthermore, these modules can be integrated together to implement a system-on-a-chip (SOC).

[0223] In the above embodiments, implementation can be achieved entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a readable storage medium or transmitted from one readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state disk (SSD)).

[0224] Figure 12 This is a schematic diagram of the structure of a terminal device provided in an embodiment of this application. Figure 12As shown, the terminal device may include: a processor 121, a memory 122, a communication interface 123, and a system bus 124. The memory 122 and the communication interface 123 are connected to the processor 121 via the system bus 124 and communicate with each other. The memory 122 is used to store computer-executed instructions, and the communication interface 123 is used to communicate with other devices. When the processor 121 executes the computer-executed instructions, it implements the following... Figures 1 to 10 The implementation scheme of the method embodiment shown.

[0225] Should Figure 12 The system bus mentioned can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The system bus can be divided into address bus, data bus, control bus, etc. For ease of representation, only one thick line is used in the diagram, but this does not indicate that there is only one bus or one type of bus. The communication interface is used to enable communication between the database access device and other devices (e.g., clients, read-write libraries, and read-only libraries). Memory may include random access memory (RAM) and may also include non-volatile memory, such as at least one disk storage device.

[0226] The processors mentioned above can be general-purpose processors, including central processing units (CPUs), network processors (NPs), etc.; they can also be digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0227] For example, embodiments of this application also provide a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform the actions described above. Figures 1 to 10 The method of the illustrated embodiment.

[0228] For example, this application embodiment also provides a chip for executing instructions, the chip being used to execute the above-mentioned instructions. Figures 1 to 10 The method of the illustrated embodiment.

[0229] In this application, "at least one" means one or more, and "more than one" means two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone, where A and B can be singular or plural. The character " / " generally indicates an "or" relationship between the preceding and following related objects; in formulas, the character " / " indicates a "division" relationship. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.

[0230] It is understood that the various numerical designations used in the embodiments of this application are merely for descriptive convenience and are not intended to limit the scope of the embodiments of this application.

[0231] It is understood that, in the embodiments of this application, the order of the above-mentioned process numbers does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

Claims

1. A fingerprint recognition method, characterized in that, include: Acquire first and second fingerprint images captured at different times; Determine the first pressure value corresponding to the first fingerprint image and the second pressure value corresponding to the second fingerprint image; When the first pressure value and the second pressure value meet different pressure levels, and both the first fingerprint image and the second fingerprint image are obtained from real fingerprints, the recognition is determined to be successful; the pressure levels include: a first pressure level less than a first pressure threshold and a second pressure level greater than a second pressure threshold, wherein the second pressure threshold is greater than the first pressure threshold; For any one of the first fingerprint image and the second fingerprint image, determine the pressure value corresponding to the fingerprint image, including: Determine the effective calculated area of ​​the fingerprint image; The pressure value corresponding to the fingerprint image is determined based on the preset correspondence between area and pressure value.

2. The method according to claim 1, characterized in that, The time interval between the acquisition of the first fingerprint image and the second fingerprint image meets a preset time interval threshold.

3. The method according to claim 1, characterized in that, The acquisition of the first fingerprint image and the second fingerprint image collected at different times includes: The system collects multiple fingerprint images when a user presses the fingerprint sensor once, with each fingerprint image carrying its own collection time and collection pressure value. Based on the acquisition time and acquisition pressure value carried in each fingerprint image frame, the first fingerprint image and the second fingerprint image are obtained from the multiple fingerprint images.

4. The method according to claim 1, characterized in that, The acquisition of the first fingerprint image and the second fingerprint image collected at different times includes: Acquire the first fingerprint image when the user presses the fingerprint sensor; Calculate the first pressure value corresponding to the first fingerprint image, and determine the pressure level to which the first pressure value belongs; A press instruction is issued based on the pressure level to which the first pressure value belongs, and the press instruction is used to instruct the user to press the fingerprint sensor with a pressure force different from the pressure level to which the first pressure value belongs; Acquire the second fingerprint image when the user presses the fingerprint sensor based on the press instruction.

5. The method according to claim 1, characterized in that, The acquisition of the first fingerprint image and the second fingerprint image collected at different times includes: The system collects multiple fingerprint images from a single press of the fingerprint sensor by the user, with each fingerprint image carrying its own acquisition time. Calculate the pressure value corresponding to each frame of the fingerprint image; Based on the pressure value corresponding to each frame of fingerprint image, the first fingerprint image and the second fingerprint image with pressure values ​​belonging to different pressure levels are obtained from the multiple frames of fingerprint images.

6. The method according to claim 1, characterized in that, Determining the effective calculated area of ​​the fingerprint image includes: Determine the imaging area coefficient of the fingerprint image; The actual imaging area in the fingerprint image is determined based on the grayscale value of each pixel in the fingerprint image and a preset grayscale threshold. The effective calculated area of ​​the fingerprint image is determined based on the imaging area coefficient and the actual imaging area.

7. The method according to claim 6, characterized in that, Determining the imaging area coefficient of the fingerprint image includes: The number of imaging pixels in the fingerprint image is counted, where the imaging pixel refers to a pixel whose grayscale value is not white; The imaging area coefficient of the fingerprint image is determined based on the number of imaging pixels in the fingerprint image and the theoretical number of pixels included in the fingerprint image.

8. The method according to claim 6, characterized in that, Determining the actual imaging area in the fingerprint image based on the grayscale value of each pixel and a preset grayscale threshold includes: The effective pixels in the fingerprint image are determined, and the effective pixels are those whose gray values ​​are less than a preset gray value threshold. The actual imaging area in the fingerprint image is determined based on the number of valid pixels in the fingerprint image.

9. The method according to claim 1, characterized in that, The method further includes: Determine the pressure level to which the first pressure value belongs; When the first pressure value belongs to the first pressure level, determine whether the first fingerprint image is obtained from a real fingerprint. When the first fingerprint image is obtained from a real fingerprint, it is determined whether the second pressure value belongs to the second pressure level; When the second pressure value belongs to the second pressure level, determine whether the second fingerprint image was obtained from a real fingerprint.

10. The method according to claim 1, characterized in that, The method further includes: Determine the pressure level to which the first pressure value belongs and the pressure level to which the second pressure value belongs; Determine whether the first pressure value and the second pressure value belong to different pressure levels; When the first pressure value and the second pressure value belong to different pressure levels, determine whether the first fingerprint image and the second fingerprint image are obtained from real fingerprints.

11. The method according to claim 9 or 10, characterized in that, For any one of the first fingerprint image and the second fingerprint image, determine whether the fingerprint image was obtained from a real fingerprint, including: The fingerprint image is input into the fingerprint recognition model to determine whether the fingerprint image was obtained from a real fingerprint. The fingerprint recognition model is a pre-trained model used to identify whether the input fingerprint image was obtained from a real fingerprint.

12. A fingerprint recognition device, characterized in that, include: The module consists of an acquisition module, a processing module, and a determination module. The acquisition module is used to acquire the first fingerprint image and the second fingerprint image collected at different times; The processing module is used to determine a first pressure value corresponding to the first fingerprint image and a second pressure value corresponding to the second fingerprint image; The determining module is used to determine successful recognition when the first pressure value and the second pressure value meet different pressure levels, and when both the first fingerprint image and the second fingerprint image are obtained from real fingerprints. The pressure levels include: a first pressure level less than a first pressure threshold and a second pressure level greater than a second pressure threshold, wherein the second pressure threshold is greater than the first pressure threshold. For any one of the first fingerprint image and the second fingerprint image, the processing module is specifically used to determine the effective calculated area of ​​the fingerprint image and determine the pressure value corresponding to the fingerprint image according to the preset correspondence between area and pressure value.

13. The apparatus according to claim 12, characterized in that, The time interval between the acquisition of the first fingerprint image and the second fingerprint image meets a preset time interval threshold.

14. The apparatus according to claim 12, characterized in that, The acquisition module is used to acquire multiple fingerprint images when a user presses the fingerprint sensor once. Each fingerprint image carries its own acquisition time and acquisition pressure value. Based on the acquisition time and acquisition pressure value carried by each fingerprint image, the first fingerprint image and the second fingerprint image are acquired from the multiple fingerprint images.

15. The apparatus according to claim 12, characterized in that, The acquisition module is configured to acquire a first fingerprint image when a user presses a fingerprint sensor, calculate a first pressure value corresponding to the first fingerprint image, determine the pressure level to which the first pressure value belongs, issue a press instruction based on the pressure level to which the first pressure value belongs, the press instruction being used to instruct the user to press the fingerprint sensor with a pressure force different from the pressure level to which the first pressure value belongs, and acquire a second fingerprint image when the user presses the fingerprint sensor based on the press instruction.

16. The apparatus according to claim 12, characterized in that, The acquisition module is specifically used to acquire multiple fingerprint images when a user presses the fingerprint sensor once. Each fingerprint image carries its own acquisition time. The module calculates the pressure value corresponding to each fingerprint image and, based on the pressure value corresponding to each fingerprint image, acquires the first fingerprint image and the second fingerprint image, whose pressure values ​​belong to different pressure levels, from the multiple fingerprint images.

17. The apparatus according to claim 12, characterized in that, The processing module is specifically used to determine the imaging area coefficient of the fingerprint image, determine the actual imaging area in the fingerprint image based on the gray value of each pixel in the fingerprint image and a preset gray value threshold, and determine the effective calculated area of ​​the fingerprint image based on the imaging area coefficient and the actual imaging area.

18. The apparatus according to claim 17, characterized in that, The processing module is specifically used to count the number of imaging pixels in the fingerprint image, where the imaging pixel refers to a pixel whose grayscale value is not white. Based on the number of imaging pixels in the fingerprint image and the theoretical number of pixels included in the fingerprint image, the imaging area coefficient of the fingerprint image is determined.

19. The apparatus according to claim 17, characterized in that, The processing module is specifically used to determine the effective pixels in the fingerprint image. The effective pixels refer to pixels whose grayscale value is less than a preset grayscale threshold. Based on the number of effective pixels in the fingerprint image, the actual imaging area in the fingerprint image is determined.

20. The apparatus according to claim 12, characterized in that, The processing module is further configured to determine the pressure level to which the first pressure value belongs, and when the first pressure value belongs to the first pressure level, determine whether the first fingerprint image is obtained by collecting a real fingerprint, when the first fingerprint image is obtained by collecting a real fingerprint, determine whether the second pressure value belongs to the second pressure level, and when the second pressure value belongs to the second pressure level, determine whether the second fingerprint image is obtained by collecting a real fingerprint.

21. The apparatus according to claim 12, characterized in that, The processing module is further configured to determine the pressure level to which the first pressure value belongs and the pressure level to which the second pressure value belongs, determine whether the first pressure value and the second pressure value belong to different pressure levels, and when the first pressure value and the second pressure value belong to different pressure levels, determine whether the first fingerprint image and the second fingerprint image are obtained from real fingerprints.

22. The apparatus according to claim 20 or 21, characterized in that, For any one of the first fingerprint image and the second fingerprint image, the processing module is further specifically used to input the fingerprint image into the fingerprint recognition model to determine whether the fingerprint image is obtained from a real fingerprint. The fingerprint recognition model is a pre-trained model used to identify whether the input fingerprint image is obtained from a real fingerprint.

23. A terminal device, comprising a processor, a memory, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the method as described in any one of claims 1-11.

24. A storage medium, characterized in that, The storage medium stores instructions that, when run on a computer, cause the computer to perform the method as described in any one of claims 1-11.

Images