Fingerprint identification method, terminal, device, storage medium and program product

Abstract

The embodiments of the present invention provide a fingerprint recognition method, a user terminal, an electronic device, a storage medium, and a computer program product. The method uses a fingerprint sensor under a display screen to collect a spatial brightness distribution map of a fingerprint image to be recognized in the current display mode of the display screen, and processes the spatial brightness distribution map of the fingerprint image to be recognized according to the current display mode to obtain a processing result. Since the embodiment of the present invention does not change the display mode of the display screen during the fingerprint recognition process, the color temperature of the display screen will not be changed, thereby avoiding the problem of screen color temperature jump and screen flicker. In addition, in the embodiment of the present invention, the spatial brightness distribution map of the fingerprint to be recognized is recognized using a live fingerprint recognition model and / or a fingerprint verification model, which can ensure the accuracy of fingerprint recognition and does not affect the anti-counterfeiting security performance of fingerprint recognition.

Description

Technical Field

[0001] Embodiments of the present invention relate to the field of information processing technology, and in particular to a fingerprint recognition method, a user terminal, an electronic device, a storage medium, and a computer program product. Background Art

[0002] With the development of smart products, the application of fingerprint recognition technology is becoming increasingly widespread. In the related art, under-screen optical fingerprint sensors require a light spot to illuminate the fingerprint for fingerprint image capture. However, because the under-screen optical fingerprint sensor is placed below the display, the RGB grayscale values ​​of the light spot corresponding to the under-screen optical fingerprint sensor are affected by the display brightness and color temperature. To ensure recognition accuracy and anti-counterfeiting security, the related art requires that the RGB grayscale values ​​of the light spot be maintained at a fixed specification when capturing the fingerprint image. Therefore, in the related art, before fingerprint image capture, the entire screen's display mode must be switched to a fixed fingerprint-specific display mode to maintain a fixed RGB grayscale value for the under-screen optical fingerprint sensor's light spot. After fingerprint recognition is completed, the entire screen's display mode is restored to the system-set display mode. This results in a significant difference in screen color temperature before and after fingerprint recognition, resulting in color temperature jumps and screen flickering. Especially in low-light environments, users perceive these screen color temperature jumps and screen flickering more strongly, causing discomfort when using the fingerprint recognition methods described in the related art.

[0003] It can be seen that there is an urgent need for a new fingerprint recognition method that aims to avoid screen color temperature jumps and screen flickering problems while ensuring recognition accuracy and anti-counterfeiting security performance. Summary of the Invention

[0004] Embodiments of the present invention provide a fingerprint recognition method, user terminal, electronic device, storage medium, and computer program product, which aim to avoid screen color temperature jumps and screen flickering problems while ensuring recognition accuracy and anti-counterfeiting security performance.

[0005] A first aspect of an embodiment of the present invention provides a fingerprint recognition method, the method comprising:

[0006] Obtaining a fingerprint image to be identified, collected by the fingerprint sensor below the display screen in the current display mode of the display screen;

[0007] Obtaining a spatial brightness distribution map of the fingerprint image to be identified, wherein the spatial brightness distribution map of the fingerprint image to be identified represents brightness distribution information of pixels in the fingerprint image to be identified;

[0008] The spatial brightness distribution map of the fingerprint image to be identified is processed according to the current display mode to obtain a liveness recognition result and / or a fingerprint verification result of the fingerprint image to be identified, wherein the liveness recognition result indicates whether the fingerprint image to be identified is an image of a real fingerprint, and the fingerprint verification result indicates whether the fingerprint image to be identified is an image of a recorded fingerprint.

[0009] Optionally, the processing of the spatial brightness distribution map of the fingerprint image to be identified according to the current display mode to obtain a liveness recognition result and / or a fingerprint verification result of the fingerprint image to be identified includes:

[0010] Inputting the current display mode and the spatial brightness distribution map of the fingerprint image to be identified into a pre-trained live fingerprint recognition model to obtain a liveness recognition result of the fingerprint image to be identified, wherein the live fingerprint recognition model has pre-learned spatial brightness distribution characteristics of images captured by the fingerprint sensor under the display screen in various display modes of the display screen for sample real fingerprints and sample prosthetic fingerprints;

[0011] and / or,

[0012] The current display mode and the spatial brightness distribution map of the fingerprint image to be identified are input into a pre-trained fingerprint verification model to obtain a fingerprint verification result of the fingerprint image to be identified; the fingerprint verification model has pre-learned the spatial brightness distribution characteristics of the image of the sample fingerprint recorded under the fingerprint sensor under various display modes of the display screen.

[0013] Optionally, obtaining a fingerprint image to be identified, which is captured by a fingerprint sensor below the display screen in a current display mode of the display screen, includes:

[0014] In the current display mode, acquiring an initial image according to an initial exposure time;

[0015] Determining an exposure time according to the brightness of the initial image, the brightness of the target image, and the initial exposure time;

[0016] Image acquisition is performed according to the exposure time to obtain the fingerprint image to be identified.

[0017] Optionally, before inputting the current display mode and the spatial brightness distribution map of the fingerprint image to be identified into a pre-trained fingerprint verification model, the method further includes:

[0018] Determining whether the liveness recognition result indicates that the fingerprint image to be recognized is an image of a real fingerprint;

[0019] Inputting the current display mode and the spatial brightness distribution map of the fingerprint image to be identified into a pre-trained fingerprint verification model includes:

[0020] When the liveness recognition result indicates that the fingerprint image to be recognized is an image of a real fingerprint, the current display mode and the spatial brightness distribution map of the fingerprint image to be recognized are input into a pre-trained fingerprint verification model.

[0021] Optionally, the method further includes:

[0022] If the fingerprint verification result indicates that the fingerprint image to be identified is an image of a recorded fingerprint, the display screen is unlocked.

[0023] Optionally, the live fingerprint recognition model is trained using a first training sample set, where the first training sample set includes training sample sets under multiple display modes of the display screen; and the step of generating a training sample pair in the training sample set under each display mode includes:

[0024] Obtaining a sample real fingerprint image collected by the fingerprint sensor below the display screen in the display mode for a real fingerprint, and a sample prosthetic fingerprint image collected for a prosthetic fingerprint;

[0025] Obtaining spatial brightness distribution maps of the sample real fingerprint image and the sample prosthetic fingerprint image;

[0026] The spatial brightness distribution graph of the sample real fingerprint image is marked with a real fingerprint label, and the spatial brightness distribution graph of the sample fake fingerprint image is marked with a fake fingerprint label, to obtain a training sample pair in this display mode.

[0027] Optionally, the fingerprint verification model is trained using a second training sample set, where the second training sample set includes training sample sets under multiple display modes of the display screen; and the step of generating a training sample in the training sample set under each display mode includes:

[0028] Obtaining a sample recorded fingerprint image collected by the fingerprint sensor below the display screen in this display mode for the sample recorded fingerprint;

[0029] A spatial brightness distribution diagram of the sample recorded fingerprint image is obtained, and an identifier indicating that the sample has been recorded fingerprint is marked on the spatial brightness distribution diagram to obtain a training sample in this display mode.

[0030] Optionally, the display screen has multiple display modes, and different display modes correspond to different color temperature conditions.

[0031] A second aspect of an embodiment of the present invention provides a fingerprint recognition device, the device comprising:

[0032] A fingerprint image acquisition module to be identified is used to obtain a fingerprint image to be identified collected by the fingerprint sensor below the display screen in the current display mode of the display screen;

[0033] A spatial brightness distribution map obtaining module is used to obtain a spatial brightness distribution map of the fingerprint image to be identified, wherein the spatial brightness distribution map of the fingerprint image to be identified represents brightness distribution information of pixels in the fingerprint image to be identified;

[0034] a processing module, configured to process the spatial brightness distribution map of the fingerprint image to be identified according to the current display mode to obtain a liveness recognition result and / or a fingerprint verification result of the fingerprint image to be identified, wherein the liveness recognition result indicates whether the fingerprint image to be identified is an image of a real fingerprint, and the fingerprint verification result indicates whether the fingerprint image to be identified is an image of a recorded fingerprint.

[0035] Optionally, the processing module includes:

[0036] a liveness recognition submodule, configured to input the current display mode and the spatial brightness distribution map of the fingerprint image to be recognized into a pre-trained liveness fingerprint recognition model to obtain a liveness recognition result for the fingerprint image to be recognized, wherein the liveness fingerprint recognition model has pre-learned the spatial brightness distribution characteristics of images captured by the fingerprint sensor below the display screen under various display modes of the display screen, for sample real fingerprints and sample prosthetic fingerprints;

[0037] and / or,

[0038] The fingerprint verification submodule is used to input the current display mode and the spatial brightness distribution map of the fingerprint image to be identified into a pre-trained fingerprint verification model to obtain a fingerprint verification result of the fingerprint image to be identified; the fingerprint verification model has pre-learned the spatial brightness distribution characteristics of the fingerprint sensor under the display screen under various display modes of the display screen for the sample fingerprint image.

[0039] Optionally, the module for obtaining the fingerprint image to be identified includes:

[0040] An initial image acquisition submodule, configured to acquire an initial image according to an initial exposure time in the current display mode;

[0041] a determination submodule, configured to determine an exposure time according to the brightness of the initial image, the brightness of the target image, and the initial exposure time;

[0042] The fingerprint image acquisition submodule to be identified is used to acquire the image according to the exposure time to obtain the fingerprint image to be identified.

[0043] Optionally, the device further comprises:

[0044] A judgment module, configured to judge whether the liveness recognition result indicates that the fingerprint image to be recognized is an image of a real fingerprint;

[0045] The fingerprint verification submodule is specifically used to:

[0046] When the liveness recognition result indicates that the fingerprint image to be recognized is an image of a real fingerprint, the current display mode and the spatial brightness distribution map of the fingerprint image to be recognized are input into a pre-trained fingerprint verification model.

[0047] Optionally, the device further comprises:

[0048] The unlocking module is used to unlock the display screen when the fingerprint verification result indicates that the fingerprint image to be identified is an image of a recorded fingerprint.

[0049] Optionally, the live fingerprint recognition model is trained using a first training sample set, where the first training sample set includes training sample sets under multiple display modes of the display screen; and the step of generating a training sample pair in the training sample set under each display mode includes:

[0050] Obtaining a sample real fingerprint image collected by the fingerprint sensor below the display screen in the display mode for a real fingerprint, and a sample prosthetic fingerprint image collected for a prosthetic fingerprint;

[0051] Obtaining spatial brightness distribution maps of the sample real fingerprint image and the sample prosthetic fingerprint image;

[0052] The spatial brightness distribution graph of the sample real fingerprint image is marked with a real fingerprint label, and the spatial brightness distribution graph of the sample fake fingerprint image is marked with a fake fingerprint label, to obtain a training sample pair in this display mode.

[0053] Optionally, the fingerprint verification model is trained using a second training sample set, where the second training sample set includes training sample sets under multiple display modes of the display screen; and the step of generating a training sample in the training sample set under each display mode includes:

[0054] Obtaining a sample recorded fingerprint image collected by the fingerprint sensor below the display screen in this display mode for the sample recorded fingerprint;

[0055] A spatial brightness distribution diagram of the sample recorded fingerprint image is obtained, and an identifier indicating that the sample has been recorded fingerprint is marked on the spatial brightness distribution diagram to obtain a training sample in this display mode.

[0056] Optionally, the display screen has multiple display modes, and different display modes correspond to different color temperature conditions.

[0057] A third aspect of an embodiment of the present invention provides a user terminal having a display screen and a fingerprint sensor located below the display screen, wherein the user terminal is configured to execute the fingerprint recognition method as described in the first aspect of the present invention.

[0058] A fourth aspect of an embodiment of the present invention provides an electronic device, including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the fingerprint recognition method as described in the first aspect of the present invention.

[0059] A fifth aspect of the embodiments of the present invention provides a computer-readable storage medium having a computer program / instruction stored thereon. When the computer program / instruction is executed by a processor, the fingerprint recognition method as described in the first aspect of the present invention is implemented.

[0060] A sixth aspect of the embodiments of the present invention provides a computer program product, including a computer program / instruction, which implements the fingerprint recognition method described in the first aspect of the present invention when executed by a processor.

[0061] In an embodiment of the present invention, a fingerprint sensor under a display screen is used to collect a spatial brightness distribution map of a fingerprint image to be identified in the current display mode of the display screen, and the spatial brightness distribution map of the fingerprint image to be identified is processed according to the current display mode to obtain a processing result. Thus, in an embodiment of the present invention, the fingerprint identification process can be completed without changing the display mode of the display screen. Moreover, in an embodiment of the present invention, the spatial brightness distribution map of the fingerprint to be identified is identified using a live fingerprint identification model and / or a fingerprint verification model, which can ensure the accuracy of fingerprint identification and does not affect the anti-counterfeiting security performance of fingerprint identification. In an embodiment of the present invention, since the display mode of the display screen is not changed during the fingerprint identification process, the color temperature of the display screen will not be changed, thereby avoiding the problem of screen color temperature jump and screen flickering.

[0062] Therefore, the fingerprint recognition method adopted in the embodiment of the present invention can avoid screen color temperature jumps and screen flickering problems while ensuring recognition accuracy and anti-counterfeiting security performance. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments of the present invention. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0064] Figure 1 is a flow chart of a fingerprint recognition method according to an embodiment of the present invention;

[0065] Figure 2 is a flow chart of another fingerprint recognition method according to an embodiment of the present invention;

[0066] Figure 3 This is a flow chart of steps for generating a training sample for a live fingerprint recognition model according to an embodiment of the present invention;

[0067] Figure 4 This is a flow chart of steps for generating a training sample for a fingerprint verification model according to an embodiment of the present invention;

[0068] Figure 5 This is a structural block diagram of a fingerprint recognition device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0069] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0070] The embodiment of the present invention aims to avoid screen color temperature jumps and screen flickering problems while ensuring recognition accuracy and anti-counterfeiting security performance. The fingerprint recognition method proposed in the embodiment of the present invention removes the restrictions on the display mode during fingerprint recognition. During the fingerprint recognition process, there is no need to switch the display mode of the display screen to a fixed fingerprint recognition mode. Instead, the color temperature conditions provided by the current display mode are used. The fingerprint sensor under the display screen is used to collect the fingerprint to be identified under the current color temperature conditions and use it for subsequent fingerprint recognition.

[0071] In an embodiment of the present invention, a pre-trained live fingerprint recognition model and / or fingerprint verification model is used to identify the spatial brightness distribution map of the fingerprint image to be identified, so that accurate identification of the image to be identified can be achieved under the color temperature conditions corresponding to any display mode. Accordingly, there is no need to set the RGB grayscale value of the light spot to remain fixed, thereby removing the restriction on the display mode during fingerprint recognition.

[0072] The fingerprint recognition method provided by the embodiment of the present invention is explained in detail below. Figure 1 , which shows a flow chart of a fingerprint recognition method according to an embodiment of the present invention. The fingerprint recognition method according to an embodiment of the present invention may specifically include the following steps:

[0073] S101, obtaining a fingerprint image to be identified, which is collected by a fingerprint sensor below the display screen in the current display mode of the display screen.

[0074] In the embodiment of the present invention, the fingerprint sensor under the display screen is affected by the color temperature conditions provided by the current display mode when collecting fingerprint images. Under different color temperature conditions, the collected fingerprint images are not exactly the same.

[0075] In an embodiment of the present invention, the display screen has multiple display modes, each corresponding to a different color temperature. Specifically, based on scene mode classification, the display screen's display modes may include: eye protection mode, reading mode, dark mode, and vivid visual effects; based on screen color classification, the display screen's display modes may include: vivid, natural, professional, and so on.

[0076] In the embodiment of the present invention, the display mode of the display screen is not adjusted, and the fingerprint sensor below the display screen collects fingerprint images under the current color temperature conditions provided by the current display mode.

[0077] In the embodiment of the present invention, under different display modes of the display screen, the corresponding RGB grayscale values ​​of the fingerprint light spot are different, which in turn causes the fingerprint light spot to have different brightness. In the embodiment of the present invention, the automatic exposure control logic of the fingerprint sensor below the display screen can be used to adjust the exposure time and adjust the average brightness of the fingerprint image (which can be simply understood as: brightness of the light spot * exposure time = average brightness) to within the normal target range.

[0078] Specifically, the following steps may be included:

[0079] S1011 : In the current display mode, capturing an initial image according to an initial exposure time.

[0080] Specifically, in an embodiment of the present invention, fingerprint images can be pre-captured based on the initial exposure time to calculate the exposure time without changing the display mode or the brightness of the light spot. The initial exposure time can be a default exposure time preset in advance by a technician.

[0081] S1012: Determine an exposure time according to the brightness of the initial image, the brightness of the target image, and the initial exposure time.

[0082] Specifically, in embodiments of the present invention, the exposure time can be determined based on the difference in brightness between the initial image and the target image and the initial exposure time. In a specific implementation, the difference in brightness between the initial image and the target image can be determined based on the difference in brightness between the initial image and the target image, or based on the ratio of the brightness of the initial image to the brightness of the target image.

[0083] S1013: Capture an image according to the exposure time to obtain the fingerprint image to be identified.

[0084] The exposure time can be automatically determined according to the light spot brightness in the current display mode and the fingerprint image target brightness required for fingerprint recognition, and the fingerprint image is collected according to the exposure time and the light spot brightness in the current display mode.

[0085] In an embodiment of the present invention, the brightness of the light spot of the fingerprint sensor below the display screen can also be adjusted to the brightest without changing the overall color temperature of the screen, so as to increase the fingerprint image acquisition speed and thus increase the overall fingerprint recognition speed.

[0086] S102: Obtain a spatial brightness distribution map of the fingerprint image to be identified, where the spatial brightness distribution map of the fingerprint image to be identified represents brightness distribution information of pixels in the fingerprint image to be identified.

[0087] In an embodiment of the present invention, the spatial brightness distribution map of the fingerprint image to be identified can be determined based on the brightness distribution information of each pixel in the fingerprint image to be identified. Alternatively, the pixels in the fingerprint image to be identified can be grouped, with the brightness distribution values ​​of the pixels in the same group being the same (for example, the average, maximum, or minimum values ​​within the same group can be used as brightness representatives), and the spatial brightness distribution map of the fingerprint image to be identified can be determined based on the brightness distribution information of each group of pixels in the fingerprint image to be identified. Grouping the pixels can also include grouping pixels that are at the same distance from a center pixel or that are within the same distance range.

[0088] In embodiments of the present invention, the average brightness of the fingerprint image to be identified, collected under different display modes, is automatically adjusted to within the normal target range after exposure. However, due to various reasons, the brightness distribution of the fingerprint image to be identified is not uniform. For example, the finger itself is not completely flat, the fingerprint itself has concave and convex textures, and / or, for example, the optical fingerprint module's lens has stronger central light and weaker edge light during imaging. Therefore, even if the average brightness of the fingerprint image to be identified is within the normal target range, the spatial brightness distribution from the inside to the outside of the fingerprint image to be identified will still vary. Based on this, embodiments of the present invention use the spatial brightness distribution map of the fingerprint image to be identified to identify the fingerprint image to be identified.

[0089] S103: Process the spatial brightness distribution map of the fingerprint image to be identified according to the current display mode to obtain a liveness recognition result and / or a fingerprint verification result of the fingerprint image to be identified.

[0090] In the embodiment of the present invention, the liveness recognition result indicates whether the fingerprint image to be identified is an image of a real fingerprint, and the fingerprint verification result indicates whether the fingerprint image to be identified is an image of a recorded fingerprint.

[0091] In the embodiment of the present invention, since the real fingerprint is not completely flat and the fingerprint itself has a concave-convex texture, the fingerprint image collected from the real fingerprint will still have differences in spatial brightness distribution from the inside to the outside due to different reflection conditions of light in different areas of the real fingerprint. However, the prosthetic fingerprint image (taking the prosthetic fingerprint image obtained from the fingerprint photo as an example) is not collected from the real fingerprint and cannot imitate the concave-convex texture of the real fingerprint. The fingerprint photo is completely flat and the reflection conditions of light in each area are similar. Therefore, the spatial brightness distribution difference from the inside to the outside of the prosthetic fingerprint image obtained is small and cannot imitate the spatial brightness distribution map of the real fingerprint image. Therefore, in the embodiment of the present invention, the spatial brightness distribution map of the fingerprint image to be identified can be processed according to the current display mode to accurately identify the spatial brightness distribution map of the real fingerprint image and the spatial brightness distribution map of the prosthetic fingerprint image.

[0092] Correspondingly, since different real fingerprints have different concave and convex textures, the reflection of light in different areas of different real fingerprints is also different. Therefore, in each display mode, the spatial brightness distribution map of different real fingerprints is also different. Therefore, the spatial brightness distribution map of the fingerprint image to be identified can also be processed according to the current display mode to identify whether the fingerprint image to be identified is an image of a recorded fingerprint.

[0093] Specifically, in the embodiment of the present invention, step S103 includes:

[0094] Inputting the current display mode and the spatial brightness distribution map of the fingerprint image to be identified into a pre-trained live fingerprint recognition model to obtain a liveness recognition result of the fingerprint image to be identified, wherein the live fingerprint recognition model has pre-learned spatial brightness distribution characteristics of images captured by the fingerprint sensor under the display screen in various display modes of the display screen for sample real fingerprints and sample prosthetic fingerprints;

[0095] and / or,

[0096] The current display mode and the spatial brightness distribution map of the fingerprint image to be identified are input into a pre-trained fingerprint verification model to obtain a fingerprint verification result of the fingerprint image to be identified; the fingerprint verification model has pre-learned the spatial brightness distribution characteristics of the image of the sample fingerprint recorded under the fingerprint sensor under various display modes of the display screen.

[0097] In the embodiment of the present invention, the spatial brightness distribution map of the fingerprint to be identified is identified using a live fingerprint identification model and / or a fingerprint verification model, which can ensure the accuracy of fingerprint identification without affecting the anti-counterfeiting security performance of fingerprint identification.

[0098] Another fingerprint recognition method is provided in the embodiment of the present invention. Figure 2 , shows a flow chart of another fingerprint recognition method according to an embodiment of the present invention, which may specifically include the following steps:

[0099] S201, obtaining a fingerprint image to be identified, which is collected by a fingerprint sensor below the display screen in the current display mode of the display screen.

[0100] S202: Obtain a spatial brightness distribution map of the fingerprint image to be identified, where the spatial brightness distribution map of the fingerprint image to be identified represents brightness distribution information of pixels in the fingerprint image to be identified.

[0101] Steps S201 - S202 are similar to the above-mentioned steps S101 - S102 and are not described in detail in this embodiment of the present invention.

[0102] S203: Input the current display mode and the spatial brightness distribution map of the fingerprint image to be identified into a pre-trained live fingerprint recognition model to obtain a liveness recognition result of the fingerprint image to be identified.

[0103] The live fingerprint recognition model pre-learns the spatial brightness distribution characteristics of images collected by the fingerprint sensor under the display screen in multiple display modes of the display screen for sample real fingerprints and sample fake fingerprints.

[0104] In the embodiment of the present invention, in actual application, a live fingerprint recognition model can be used to perform liveness recognition on the fingerprint first. If the liveness recognition is successful, fingerprint verification can be performed, which can further improve the overall efficiency of the fingerprint recognition method.

[0105] In other optional embodiments, fingerprint verification may be performed first, and then live fingerprint recognition may be performed on the fingerprint using a live fingerprint recognition model. If both fingerprint verification and live fingerprint recognition are passed, it indicates that fingerprint recognition is successful.

[0106] S204: Determine whether the liveness recognition result indicates that the fingerprint image to be recognized is an image of a real fingerprint.

[0107] In the embodiment of the present invention, when it is determined that the fingerprint image to be identified is an image of a real fingerprint, that is, when the liveness identification is passed, the next step of fingerprint verification is performed.

[0108] S205: When the liveness recognition result indicates that the fingerprint image to be recognized is an image of a real fingerprint, the current display mode and the spatial brightness distribution map of the fingerprint image to be recognized are input into a pre-trained fingerprint verification model.

[0109] S206 , when the fingerprint verification result indicates that the fingerprint image to be identified is an image of a recorded fingerprint, unlock the display screen.

[0110] The fingerprint recognition method provided in the embodiment of the present invention can be used for fingerprint unlocking, and can also be used in application scenarios that require fingerprint recognition, such as fingerprint payment and fingerprint login.

[0111] When the fingerprint recognition method provided by the embodiment of the present invention is used for fingerprint unlocking, fingerprint verification can be performed after the liveness recognition is passed. When the verification determines that the fingerprint image to be recognized is an image of the recorded fingerprint, the display screen is unlocked.

[0112] In the embodiment of the present invention, when fingerprint recognition fails, the reason for the failure (for example, liveness recognition failure or fingerprint verification failure) may also be returned.

[0113] In an optional embodiment of the present invention, the live fingerprint recognition model is trained using a first training sample set, which includes training sample sets under multiple display modes of the display screen. The embodiment of the present invention also provides a flow chart of the steps for generating training samples, such as Figure 3 As shown, the steps for generating a training sample pair in the training sample set in each display mode include:

[0114] S301, obtaining a sample real fingerprint image collected by the fingerprint sensor below the display screen in this display mode for a real fingerprint, and a sample prosthetic fingerprint image collected for a prosthetic fingerprint.

[0115] S302: Obtain spatial brightness distribution maps of the sample real fingerprint image and the sample prosthetic fingerprint image.

[0116] S303: Mark the spatial brightness distribution graph of the sample real fingerprint image with a real fingerprint label, and mark the spatial brightness distribution graph of the sample prosthetic fingerprint image with a prosthetic fingerprint label, to obtain a training sample pair in this display mode.

[0117] In this embodiment of the present invention, when the current display screen is in display mode A1, under the color temperature provided by display mode A1, the RGB grayscale values ​​of the fingerprint spot are R1:G1:B1, and the corresponding brightness of the displayed spot is a1. After automatic exposure by the fingerprint sensor below the display screen, the optimal exposure times for the real fingerprint and the prosthetic fingerprint are determined to be t1 and s1, respectively, as well as the spatial brightness distribution maps H1 and L1 of the real fingerprint image and the prosthetic fingerprint image, respectively. H1 is labeled with the real fingerprint label, and L1 is labeled with the prosthetic fingerprint label, resulting in a training sample pair under the color temperature conditions corresponding to display mode A1.

[0118] Correspondingly, by adopting the same method, other training sample pairs under the color temperature condition corresponding to the display mode A1 can be obtained.

[0119] Correspondingly, by adopting the same method, multiple training sample pairs under the color temperature condition corresponding to the display mode A2 can be obtained.

[0120] In this embodiment of the present invention, a pre-set model is trained using training samples containing images of both prosthetic and real fingerprints to generate a live fingerprint recognition model. This model can then learn the spatial luminance distribution characteristics of real fingerprint images generated by the fingerprint sensor beneath the display under various display color temperature conditions. This trained live fingerprint recognition model can then distinguish between real and prosthetic fingerprints.

[0121] In an optional embodiment of the present invention, the fingerprint verification model is trained using a second training sample set, and the second training sample set includes training sample sets under various color temperature conditions of the display screen, such as Figure 4 As shown, the steps for generating a training sample in the training sample set under each color temperature condition include:

[0122] S401, obtaining a sample recorded fingerprint image collected by the fingerprint sensor below the display screen in this display mode for the sample recorded fingerprint.

[0123] S402: Obtain a spatial brightness distribution diagram of the sample recorded fingerprint image, and mark the spatial brightness distribution diagram with an identifier indicating that the sample has recorded fingerprint, thereby obtaining a training sample in this display mode.

[0124] In an embodiment of the present invention, the training sample generation method provided in the above steps S301-S303 can be used to obtain spatial brightness distribution diagrams H1, H2, H3...Hn of multiple fingerprint images under the color temperature conditions corresponding to the display mode A1. The spatial brightness distribution diagram of the sample recorded fingerprint is marked with the corresponding sample recorded fingerprint ID, for example: H1 is marked with the recorded fingerprint ID1. Finally, the training samples marked with the recorded fingerprint ID and other training samples not marked with the recorded fingerprint ID are input into the preset model for training to obtain a fingerprint verification model. In this way, the fingerprint verification model can learn the spatial brightness distribution characteristics of the sample recorded fingerprint image under the fingerprint sensor under the various color temperature conditions of the display screen.

[0125] Based on the same inventive concept, an embodiment of the present invention provides a fingerprint recognition device. Figure 5 , Figure 5 FIG is a schematic diagram of a fingerprint recognition device provided by an embodiment of the present invention. Figure 5As shown, the fingerprint recognition device 500 includes:

[0126] The fingerprint image acquisition module 501 is used to obtain the fingerprint image to be identified, which is collected by the fingerprint sensor below the display screen in the current display mode of the display screen;

[0127] A spatial brightness distribution map obtaining module 502 is configured to obtain a spatial brightness distribution map of the fingerprint image to be identified, wherein the spatial brightness distribution map of the fingerprint image to be identified represents brightness distribution information of pixels in the fingerprint image to be identified;

[0128] The processing module 503 is used to process the spatial brightness distribution map of the fingerprint image to be identified according to the current display mode to obtain a liveness recognition result and / or a fingerprint verification result of the fingerprint image to be identified, wherein the liveness recognition result indicates whether the fingerprint image to be identified is an image of a real fingerprint, and the fingerprint verification result indicates whether the fingerprint image to be identified is an image of a recorded fingerprint.

[0129] Optionally, the processing module 503 includes:

[0130] a liveness recognition submodule, configured to input the current display mode and the spatial brightness distribution map of the fingerprint image to be recognized into a pre-trained liveness fingerprint recognition model to obtain a liveness recognition result for the fingerprint image to be recognized, wherein the liveness fingerprint recognition model has pre-learned the spatial brightness distribution characteristics of images captured by the fingerprint sensor below the display screen under various display modes of the display screen, for sample real fingerprints and sample prosthetic fingerprints;

[0131] and / or,

[0132] The fingerprint verification submodule is used to input the current display mode and the spatial brightness distribution map of the fingerprint image to be identified into a pre-trained fingerprint verification model to obtain a fingerprint verification result of the fingerprint image to be identified; the fingerprint verification model has pre-learned the spatial brightness distribution characteristics of the fingerprint sensor under the display screen under various display modes of the display screen for the sample fingerprint image.

[0133] Optionally, the fingerprint image to be identified obtaining module 501 includes:

[0134] An initial image acquisition submodule, configured to acquire an initial image according to an initial exposure time in the current display mode;

[0135] a determination submodule, configured to determine an exposure time according to the brightness of the initial image, the brightness of the target image, and the initial exposure time;

[0136] The fingerprint image acquisition submodule to be identified is used to acquire the image according to the exposure time to obtain the fingerprint image to be identified.

[0137] Optionally, the device further comprises:

[0138] A judgment module, configured to judge whether the liveness recognition result indicates that the fingerprint image to be recognized is an image of a real fingerprint;

[0139] The fingerprint verification submodule is specifically used to:

[0140] When the liveness recognition result indicates that the fingerprint image to be recognized is an image of a real fingerprint, the current display mode and the spatial brightness distribution map of the fingerprint image to be recognized are input into a pre-trained fingerprint verification model.

[0141] Optionally, the device further comprises:

[0142] The unlocking module is used to unlock the display screen when the fingerprint verification result indicates that the fingerprint image to be identified is an image of a recorded fingerprint.

[0143] Optionally, the live fingerprint recognition model is trained using a first training sample set, where the first training sample set includes training sample sets under multiple display modes of the display screen; and the step of generating a training sample pair in the training sample set under each display mode includes:

[0144] Obtaining a sample real fingerprint image collected by the fingerprint sensor below the display screen in the display mode for a real fingerprint, and a sample prosthetic fingerprint image collected for a prosthetic fingerprint;

[0145] Obtaining spatial brightness distribution maps of the sample real fingerprint image and the sample prosthetic fingerprint image;

[0146] The spatial brightness distribution graph of the sample real fingerprint image is marked with a real fingerprint label, and the spatial brightness distribution graph of the sample fake fingerprint image is marked with a fake fingerprint label, to obtain a training sample pair in this display mode.

[0147] Optionally, the fingerprint verification model is trained using a second training sample set, where the second training sample set includes training sample sets under multiple display modes of the display screen; and the step of generating a training sample in the training sample set under each display mode includes:

[0148] Obtaining a sample recorded fingerprint image collected by the fingerprint sensor below the display screen in this display mode for the sample recorded fingerprint;

[0149] A spatial brightness distribution diagram of the sample recorded fingerprint image is obtained, and an identifier indicating that the sample has been recorded fingerprint is marked on the spatial brightness distribution diagram to obtain a training sample in this display mode.

[0150] Optionally, the display screen has multiple display modes, and different display modes correspond to different color temperature conditions.

[0151] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0152] An embodiment of the present invention further provides a user terminal having a display screen and a fingerprint sensor below the display screen, wherein the user terminal is configured to execute the fingerprint recognition method as described in any embodiment of the present invention.

[0153] Based on the same inventive concept, an embodiment of the present invention further provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the fingerprint recognition method as described in any embodiment of the present invention.

[0154] Based on the same inventive concept, an embodiment of the present invention further provides a computer-readable storage medium having a computer program / instruction stored thereon. When the computer program / instruction is executed by a processor, the fingerprint recognition method as described in any embodiment of the present invention is implemented.

[0155] Based on the same inventive concept, an embodiment of the present invention further provides a computer program product, including a computer program / instruction, which implements the fingerprint recognition method as described in any embodiment of the present invention when executed by a processor.

[0156] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0157] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, apparatus, or computer program products. Thus, embodiments of the present invention may take the form of a fully hardware embodiment, a fully software embodiment, or an embodiment combining software and hardware. Furthermore, embodiments of the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0158] The embodiments of the present invention are described with reference to the flowcharts and / or block diagrams of the methods, terminal devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing terminal device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing terminal device generate instructions for implementing the process in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0159] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing terminal device to operate in a specific manner, so that the instructions stored in the computer readable memory produce a manufactured product including an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0160] These computer program instructions can also be loaded onto a computer or other programmable data processing terminal device so that a series of operating steps are executed on the computer or other programmable terminal device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable terminal device to implement the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0161] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they become aware of the basic creative concepts. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present invention.

[0162] Finally, it should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device that includes a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or terminal device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of additional identical elements in the process, method, article, or terminal device that includes the element.

[0163] The above is a detailed introduction to the fingerprint recognition method, user terminal, electronic device, storage medium and computer program product provided by the present invention. Specific examples are used herein to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only intended to help understand the method and core ideas of the present invention. At the same time, for those skilled in the art, according to the ideas of the present invention, there may be changes in the specific implementation methods and application scopes. In summary, the contents of this specification should not be understood as limiting the present invention.

Claims

1. A fingerprint recognition method, characterized in that: The method comprises: Obtaining a fingerprint image to be identified, collected by the fingerprint sensor below the display screen in the current display mode of the display screen; Obtaining a spatial brightness distribution map of the fingerprint image to be identified, wherein the spatial brightness distribution map of the fingerprint image to be identified represents brightness distribution information of pixels in the fingerprint image to be identified; The spatial brightness distribution map of the fingerprint image to be identified is processed according to the current display mode to obtain a liveness recognition result and / or a fingerprint verification result of the fingerprint image to be identified, wherein the liveness recognition result indicates whether the fingerprint image to be identified is an image of a real fingerprint, and the fingerprint verification result indicates whether the fingerprint image to be identified is an image of a recorded fingerprint.

2. The fingerprint recognition method according to claim 1, characterized in that: The processing of the spatial brightness distribution map of the fingerprint image to be identified according to the current display mode to obtain a liveness recognition result and / or a fingerprint verification result of the fingerprint image to be identified includes: Inputting the current display mode and the spatial brightness distribution map of the fingerprint image to be identified into a pre-trained live fingerprint recognition model to obtain a liveness recognition result of the fingerprint image to be identified, wherein the live fingerprint recognition model has pre-learned spatial brightness distribution characteristics of images captured by the fingerprint sensor under the display screen in various display modes of the display screen for sample real fingerprints and sample prosthetic fingerprints; and / or, The current display mode and the spatial brightness distribution map of the fingerprint image to be identified are input into a pre-trained fingerprint verification model to obtain a fingerprint verification result of the fingerprint image to be identified; the fingerprint verification model has pre-learned the spatial brightness distribution characteristics of the image of the sample fingerprint recorded under the fingerprint sensor under various display modes of the display screen.

3. The fingerprint recognition method according to claim 2, characterized in that: The obtaining of the fingerprint image to be identified, which is collected by the fingerprint sensor below the display screen in the current display mode of the display screen, includes: In the current display mode, acquiring an initial image according to an initial exposure time; Determining an exposure time according to the brightness of the initial image, the brightness of the target image, and the initial exposure time; Image acquisition is performed according to the exposure time to obtain the fingerprint image to be identified.

4. The fingerprint recognition method according to claim 3, characterized in that: Before inputting the current display mode and the spatial brightness distribution map of the fingerprint image to be identified into a pre-trained fingerprint verification model, the method further includes: Determining whether the liveness recognition result indicates that the fingerprint image to be recognized is an image of a real fingerprint; Inputting the current display mode and the spatial brightness distribution map of the fingerprint image to be identified into a pre-trained fingerprint verification model includes: When the liveness recognition result indicates that the fingerprint image to be recognized is an image of a real fingerprint, the current display mode and the spatial brightness distribution map of the fingerprint image to be recognized are input into a pre-trained fingerprint verification model.

5. The fingerprint recognition method according to any one of claims 1 to 4, characterized in that: The method further comprises: If the fingerprint verification result indicates that the fingerprint image to be identified is an image of a recorded fingerprint, the display screen is unlocked.

6. The fingerprint recognition method according to any one of claims 2 to 4, characterized in that: The live fingerprint recognition model is trained using a first training sample set, wherein the first training sample set includes training sample sets under multiple display modes of the display screen; The steps for generating a training sample pair in the training sample set for each display mode include: Obtaining a sample real fingerprint image collected by the fingerprint sensor below the display screen in the display mode for a real fingerprint, and a sample prosthetic fingerprint image collected for a prosthetic fingerprint; Obtaining spatial brightness distribution maps of the sample real fingerprint image and the sample prosthetic fingerprint image; The spatial brightness distribution graph of the sample real fingerprint image is marked with a real fingerprint label, and the spatial brightness distribution graph of the sample fake fingerprint image is marked with a fake fingerprint label, to obtain a training sample pair in this display mode.

7. The fingerprint recognition method according to any one of claims 2 to 4, characterized in that: The fingerprint verification model is trained using a second training sample set, wherein the second training sample set includes training sample sets under multiple display modes of the display screen; The steps for generating a training sample in the training sample set for each display mode include: Obtaining a sample recorded fingerprint image collected by the fingerprint sensor below the display screen in this display mode for the sample recorded fingerprint; A spatial brightness distribution diagram of the sample recorded fingerprint image is obtained, and an identifier indicating that the sample has been recorded fingerprint is marked on the spatial brightness distribution diagram to obtain a training sample in this display mode.

8. The fingerprint recognition method according to any one of claims 1 to 7, characterized in that: The display screen has multiple display modes, and different display modes correspond to different color temperature conditions.

9. A user terminal comprising a display screen and a fingerprint sensor located below the display screen, wherein the user terminal is configured to execute the fingerprint recognition method according to any one of claims 1 to 8.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory, wherein: The processor executes the computer program to implement the fingerprint recognition method according to any one of claims 1 to 8.

11. A computer-readable storage medium having a computer program / instruction stored thereon, characterized in that: When the computer program / instruction is executed by a processor, the fingerprint recognition method according to any one of claims 1 to 8 is implemented.

12. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instruction is executed by a processor, the fingerprint recognition method according to any one of claims 1 to 8 is implemented.

Images