Fingerprint recognition method, display module and display device

Abstract

The present disclosure provides a fingerprint recognition method, a display module and a display device, which belong to the field of display technology and can solve the problem that the existing fingerprint recognition system is easily attacked by fake fingerprints. The fingerprint recognition method disclosed in the present disclosure is used to recognize the texture on the surface of the touch subject, including: generating a recognition image according to the light signal reflected by the texture on the surface of the touch subject; determining the grayscale value variation law of at least part of the area in the recognition image; judging whether the texture on the surface of the touch subject is a real fingerprint or a fake fingerprint according to the grayscale value variation law of at least part of the area in the recognition image.

Description

Technical Field

[0001] The present disclosure belongs to the field of display technology, and specifically relates to a fingerprint recognition method, a display module and a display device. Background Art

[0002] With the widespread popularization of optical fingerprint recognition technology in mobile smart terminals, optical fingerprint recognition technology is being more and more widely used in fingerprint unlocking, mobile payment, software encryption and other scenarios of terminal devices such as mobile phones. People have also put forward higher requirements on the security of fingerprint recognition systems in terminal devices.

[0003] At present, fake fingerprints made by printing the residual fingerprints on the surface of objects or fingerprint images can be used to deceive the fingerprint recognition system of terminal devices such as mobile phones, thus bringing potential risks. Therefore, resisting fake fingerprint attacks is of great significance to the security of fingerprint recognition systems in terminal devices such as mobile phones. Summary of the invention

[0004] The present disclosure aims to solve at least one of the technical problems existing in the prior art and provides a fingerprint recognition method, a display module and a display device.

[0005] In a first aspect, an embodiment of the present disclosure provides a fingerprint recognition method for identifying patterns on a surface of a touch subject, the fingerprint recognition method comprising:

[0006] generating an identification image according to light signals reflected by the textures on the surface of the touch body;

[0007] Determining a grayscale value variation rule of at least a portion of the identified image;

[0008] According to the grayscale value variation rule of at least a part of the area in the recognition image, it is determined whether the texture on the surface of the touch body is a real fingerprint or a fake fingerprint.

[0009] Optionally, the recognition image has a central area and an edge area surrounding the central area; and judging whether the texture on the surface of the touch subject is a real fingerprint or a fake fingerprint according to a change rule of grayscale values ​​of at least a part of the area in the recognition image includes:

[0010] Determine whether the grayscale value variation rule of the edge area of ​​the recognition image conforms to a first preset variation rule; the first preset variation rule is the grayscale value variation rule of the edge area of ​​the real fingerprint recognition image extracted by using a neural network model;

[0011] If the grayscale value variation rule of the edge area of ​​the recognition image conforms to the first preset variation rule, it is determined that the texture on the surface of the touch body is a real fingerprint.

[0012] Optionally, the first preset change rule includes that the slope of the change curve formed by each of the grayscale values ​​in the edge area of ​​the true fingerprint recognition image is greater than the first preset slope and less than the second preset slope, and the width of the edge area is greater than the first preset width and less than the second preset width.

[0013] Optionally, the recognition image has a central area and an edge area surrounding the central area; and judging whether the texture on the surface of the touch subject is a real fingerprint or a fake fingerprint according to a change rule of grayscale values ​​of at least a part of the area in the recognition image includes:

[0014] Determine whether the grayscale value variation rule of the central area of ​​the recognition image conforms to a second preset variation rule; the second preset variation rule is the grayscale value variation rule of the central area of ​​the real fingerprint recognition image extracted by using a neural network model;

[0015] If the grayscale value variation rule of the central area of ​​the recognition image conforms to the second preset variation rule, it is determined that the texture on the surface of the touch body is a true fingerprint.

[0016] Optionally, the texture on the surface of the touch body includes: valleys and ridges; the second preset change rule includes that in the central area of ​​the true fingerprint recognition image, from the top of the ridge to the bottom of the valley, the slope of the change curve formed by each grayscale value is greater than the third preset slope and less than the fourth preset slope, and the width from the top of the ridge to the bottom of the valley in the central area is greater than the third preset width and less than the fourth preset width.

[0017] Optionally, the texture on the surface of the touch body includes: valleys and ridges; the second preset change rule includes that in the central area of ​​the true fingerprint recognition image, from the bottom of the valley to the top of the ridge, the slope of the change curve formed by each grayscale value is greater than the fifth preset slope and less than the sixth preset slope, and the width from the bottom of the valley to the top of the ridge in the central area is greater than the fifth preset width and less than the sixth preset width.

[0018] In a second aspect, an embodiment of the present disclosure provides a display module, comprising: a substrate, a display panel located on the substrate, and a plurality of image sensors located between the substrate and the display panel, wherein the display module further comprises: an image processor connected to the image sensor; the image processor is used to:

[0019] generating an identification image according to light signals reflected by the textures on the surface of the touch body;

[0020] Determining a grayscale value variation rule of at least a portion of the identified image;

[0021] According to the grayscale value variation rule of at least a part of the area in the recognition image, it is determined whether the texture on the surface of the touch body is a real fingerprint or a fake fingerprint.

[0022] Optionally, the display module further comprises: a collimation structure located between the image sensor and the display panel;

[0023] The collimating structure includes a fiber optic plate or a plurality of micro lenses arranged in an array.

[0024] Optionally, when the surface of the touch body contacts the display panel, an orthographic projection of the surface of the touch body on the substrate falls within an orthographic projection of the plurality of image sensors on the substrate.

[0025] In a third aspect, an embodiment of the present disclosure provides a display device, comprising the display module provided as described above. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 A schematic diagram of a fingerprint recognition method provided by an embodiment of the present disclosure;

[0027] Figure 2 This is a schematic diagram of the optical path of light reflected from a real fingerprint;

[0028] Figure 3 This is a schematic diagram of the optical path of light reflected from another real fingerprint;

[0029] Figure 4 A schematic diagram of the structure of a display module provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0030] In order to enable those skilled in the art to better understand the technical solution of the present disclosure, the present disclosure is further described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0031] Unless otherwise defined, the technical terms or scientific terms used in the present disclosure should be understood by people with ordinary skills in the field to which the present disclosure belongs. The "first", "second" and similar words used in the present disclosure do not indicate any order, quantity or importance, but are only used to distinguish different components. Similarly, similar words such as "one", "one" or "the" do not indicate quantity restrictions, but indicate that there is at least one. Similar words such as "include" or "comprise" mean that the elements or objects appearing before the word cover the elements or objects listed after the word and their equivalents, without excluding other elements or objects. Similar words such as "connect" or "connected" are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0032] The epidermis of human fingers is uneven and has a three-dimensional structure of valleys and ridges. When the finger is pressed on the screen of the terminal device, the ridge of the finger is in direct contact with the screen, and there is an air gap between the valley of the finger and the screen. Since the refractive index of the epidermis of the finger and the air is different for light, the valleys and ridges of the finger reflect different intensities of light emitted by the screen, so that the corresponding image sensors under the valleys and ridges receive different intensities of light, so that the valleys and ridges of the fingerprint can be displayed on the identification image. Then the identification image is compared with the pre-stored image in the image library. If the identification image matches the pre-stored image in the image library, the fingerprint is determined to be an authenticated fingerprint to realize the optical fingerprint recognition function. It should be noted here that the above-mentioned terminal device can be a mobile phone, tablet computer, laptop computer, smart door lock and other devices with optical fingerprint recognition function. In the following description, a mobile phone with optical fingerprint recognition function will be described as an example. The current optical fingerprint recognition technology is widely used in scenarios such as fingerprint unlocking, mobile payment, and software encryption. However, based on the current fingerprint recognition technology, fake fingerprints produced by obtaining residual fingerprints on the surface of objects or fingerprint images and printing them can be used to deceive the fingerprint recognition system of mobile phones, thus bringing potential risks.

[0033] In order to solve at least one of the above technical problems, the embodiments of the present disclosure provide a fingerprint recognition method, a display module and a display device. The fingerprint recognition method, the display module and the display device provided by the embodiments of the present disclosure will be further described in detail below in combination with the accompanying drawings and specific implementation methods.

[0034] Embodiment 1

[0035] Figure 1A schematic diagram of a fingerprint recognition method provided by an embodiment of the present disclosure is provided. The fingerprint recognition method can be used to recognize the texture on the surface of a touch object, such as Figure 1 As shown, the fingerprint recognition method provided by the embodiment of the present disclosure includes the following steps:

[0036] S101, generating a recognition image according to light signals reflected by textures on the surface of a touch subject.

[0037] It should be noted that the touch subject here can be a finger or other object covered with fake fingerprints. When the surface of the finger or other object is pressed on the mobile phone screen, the light emitted by the mobile phone screen can be irradiated to the surface of the finger or other object, and the texture on the surface can reflect the light to form a reflected light signal. Since the reflection intensity of light is different at different positions in the texture on the surface of the finger or other object, an identification image for the texture on the surface of the finger or other object can be generated based on the reflected light signal.

[0038] S102, determining a change rule of the grayscale value of at least a partial area in the recognition image.

[0039] It should be noted that at least a partial area in the recognition image can be detected to extract multiple grayscale values ​​in the area in the recognition image. The multiple grayscale values ​​here can be the grayscale values ​​of the pixels along the same direction in the recognition image. In order to facilitate detection and extraction, each grayscale value can be the average of the grayscale values ​​of multiple pixels. Since the reflection intensity of light is different for the lines at different positions on the surface of the finger or other object, the grayscale values ​​in the generated recognition image are also different, and there is a certain preset change rule, which can be the change rule of the grayscale value in the real fingerprint recognition image extracted using the neural network model.

[0040] S103, judging whether the texture on the surface of the touch subject is a real fingerprint or a fake fingerprint according to a change rule of the grayscale value of at least a part of the area in the recognition image.

[0041] It should be noted that the fingerprint of a finger is uneven, with the raised part being the ridge and the sunken part being the valley. Each valley and ridge has a flat surface, so the grayscale value of at least part of the area in the corresponding generated recognition image also has a certain preset change rule. However, the current fake fingerprints are generally produced by obtaining the residual imprint of the fingerprint on the surface of the object or the fingerprint image, etc., and then printed. It cannot accurately copy the valleys and ridges in the fingerprint of the finger to form an accurate three-dimensional structure. Therefore, when the fake fingerprint presses the mobile phone screen, the change rule of the grayscale value in the corresponding recognition image may not meet the above preset change rule. In this way, it is possible to judge whether the texture on the surface of the touch subject is a real fingerprint or a fake fingerprint based on the change rule of the grayscale value of at least part of the area in the recognition image.

[0042] In the fingerprint recognition method provided by the embodiment of the present disclosure, it is possible to identify whether the texture on the surface of the touch subject is a fake fingerprint based on the change pattern of the grayscale value of at least a part of the area in the recognition image generated for the texture on the surface of the touch subject, which can effectively avoid the problem of using fake fingerprints to attack the fingerprint recognition system, thereby improving the security of the fingerprint recognition system and thus improving the user experience. On the other hand, the fingerprint recognition method provided by the embodiment of the present disclosure does not require adding additional components to the original fingerprint recognition system, and the recognition method is simple and fast, which can effectively save costs while resisting fake fingerprint attacks.

[0043] In some embodiments, the recognition image has a central area and an edge area surrounding the central area; the above-mentioned step S103, according to the grayscale value change law of at least part of the area in the recognition image, determines whether the texture on the surface of the touch body is a real fingerprint or a fake fingerprint, including: determining whether the grayscale value change law of the edge area of ​​the recognition image conforms to a first preset change law; the first preset change law is the grayscale value change law of the edge area of ​​the real fingerprint recognition image extracted by using the neural network model; if the grayscale value change law of the edge area of ​​the recognition image conforms to the first preset change law, it is determined that the texture on the surface of the touch body is a real fingerprint.

[0044] It should be noted that Figure 2 A schematic diagram of the optical path of light reflected from a real fingerprint is shown in FIG. Figure 2As shown, the fingerprint at the edge of the finger is not in contact with the mobile phone screen, and the edge of the finger is getting farther and farther away from the mobile phone screen. The fingerprint at the edge of the finger can reflect the light emitted by the mobile phone screen and form a light signal, thereby generating an identification image. Since the distance between the edge of the finger and the mobile phone screen is much greater than the depth of the valley in the fingerprint of the finger, it is not necessary to consider the influence of the valley and ridge at the edge of the finger on the reflection of light. As the distance between the fingerprint at different positions of the edge of the finger gradually increases from the mobile phone screen, the reflection ability gradually weakens, and the grayscale value gradually decreases. A neural network model can be used to collect a large number of identification images of real fingerprints to form a first preset change law of the grayscale value of the edge area of ​​the real fingerprint identification image. However, for the false fingerprint made by printing, the structure of the valley and ridge therein is not exactly the same as the structure of the valley and ridge in the real fingerprint. Therefore, in the identification image generated for the false fingerprint, the grayscale value change law of its edge area does not conform to the first preset change law. In this way, the texture on the surface of the touch subject can be identified as a true fingerprint or a false fingerprint by identifying whether the change law of the grayscale value in the edge area of ​​the image conforms to the first preset change law. If the grayscale value change pattern of the edge area of ​​the identified image conforms to the first preset change pattern, the texture on the surface of the touch body is determined to be a real fingerprint; if the grayscale value change pattern of the edge area of ​​the identified image does not conform to the first preset change pattern, the texture on the surface of the touch body is determined to be a fake fingerprint.

[0045] In some embodiments, the first preset change rule includes that the slope of the change curve formed by each grayscale value in the edge area of ​​the true fingerprint recognition image is greater than the first preset slope and less than the second preset slope, and the width of the edge area is greater than the first preset width and less than the second preset width.

[0046] It should be noted that if Figure 2As shown, as the distance between the fingerprint at different positions of the edge of the finger and the mobile phone screen gradually increases, the reflective ability gradually weakens, and the grayscale value gradually decreases. The grayscale values ​​corresponding to the edge of the finger form a change curve, and the slope of the change curve of the grayscale value changes within a certain range, for example, the slope of the change curve changes between the first slope and the second slope, wherein the first slope can be 0.5DN / μm, and the second slope can be 1.5DN / μm. It should be noted that the data extracted in the embodiment of the present disclosure are all described as 16-bit images. At the same time, the width of the edge area in the recognition image also changes within a certain range, for example, the width of the edge area changes between the first preset width and the second preset width, wherein the first preset width can be 1.4 mm, and the second preset width can be 2.5 mm. In practical applications, the grayscale values ​​of the pixels between 1.4 mm and 2.5 mm in the recognition image can be selected, and the lines on the surface of the touch body can be identified as true fingerprints or false fingerprints by judging whether the slope of the change curve formed by each grayscale value changes within the range of 0.5DN / μm to 1.5DN / μm.

[0047] In some embodiments, the recognition image has a central area and an edge area surrounding the central area; the above-mentioned step S103, according to the grayscale value change rule of at least part of the area in the recognition image, determines whether the texture on the surface of the touch body is a real fingerprint or a fake fingerprint, including: determining whether the grayscale value change rule of the central area of ​​the recognition image conforms to a second preset change rule; the second preset change rule is the grayscale value change rule of the central area of ​​the real fingerprint recognition image extracted by using the neural network model; if the grayscale value change rule of the central area of ​​the recognition image conforms to the second preset change rule, it is determined that the texture on the surface of the touch body is a real fingerprint.

[0048] It should be noted that Figure 3 This is a schematic diagram of the optical path of another type of genuine fingerprint reflected light, such as Figure 3As shown, the fingerprint at the center of the finger is in contact with the mobile phone screen, and the reflection intensity of the valley and ridge of the finger for light is different. Since the ridge is in contact with the mobile phone screen, there is no air gap between them, and most of the light emitted by the mobile phone screen is transmitted through the ridge of the finger, so the ridge of the finger has a weak ability to reflect light. Since there is a certain air gap between the valley and the mobile phone screen, and the refractive index of air and the surface of the mobile phone is different, the light can be reflected at the boundary of the air gap formed by the mobile phone screen and the valley of the finger, and at the same time, the top position of the corresponding valley can form a convergence effect on the light, resulting in a strong ability of the top of the valley to reflect light, and a larger grayscale value in the corresponding recognition image, and a position far from the top of the valley has a weaker ability to reflect light, and a smaller grayscale value in the corresponding recognition image. A neural network model can be used to collect a large number of recognition images of real fingerprints to form a second preset change law of the grayscale value in the central area of ​​the real fingerprint recognition image. However, for a fake fingerprint made by printing, the structure of the valley and ridge therein is not exactly the same as the structure of the valley and ridge in the real fingerprint. Therefore, in the recognition image generated for the fake fingerprint, the grayscale value change law of its central area does not conform to the second preset change law. In this way, the texture on the surface of the touch subject can be identified as a true fingerprint or a false fingerprint by identifying whether the change rule of the grayscale value in the central area of ​​the image conforms to the second preset change rule. If the change rule of the grayscale value in the central area of ​​the image conforms to the second preset change rule, the texture on the surface of the touch subject is determined to be a true fingerprint; if the change rule of the grayscale value in the central area of ​​the image does not conform to the second preset change rule, the texture on the surface of the touch subject is determined to be a false fingerprint.

[0049] In some embodiments, the texture on the surface of the touch body includes: valleys and ridges; the second preset change rule includes that in the central area of ​​the true fingerprint recognition image, the slope of the change curve formed by each grayscale value from the top of the ridge to the bottom of the valley is greater than the third preset slope and less than the fourth preset slope, and the width from the top of the ridge to the bottom of the valley in the central area is greater than the third preset width and less than the fourth preset width.

[0050] It should be noted that if Figure 3As shown, since there is a certain air gap between the valley and the mobile phone screen, and the refractive index of air and the surface of the mobile phone is different, the light can be reflected at the boundary of the air gap formed by the mobile phone screen and the valley of the finger, and the corresponding top position of the valley can form a converging effect on the light, resulting in a stronger ability of the top of the valley to reflect light, and a larger grayscale value in the corresponding recognition image, and a weaker ability of the position far away from the top of the valley to reflect light, and a smaller grayscale value in the corresponding recognition image. The grayscale values ​​corresponding to the top of the ridge to the bottom of the valley in the central area of ​​the finger are formed into a change curve, and the slope of the change curve of the grayscale value changes within a certain range, for example, the slope of the change curve changes between the third slope and the fourth slope, wherein the third slope can be 2.1DN / μm, and the fourth slope can be 3.2DN / μm. At the same time, the width from the top of the ridge to the bottom of the valley in the central area of ​​the recognition image also changes within a certain range, for example, the width from the top of the ridge to the bottom of the valley in the central area changes between the third preset width and the fourth preset width, wherein the third preset width can be 150 microns, and the fourth preset width can be 300 microns. In practical applications, the grayscale values ​​of pixels between 150 microns and 300 microns in the central area of ​​the image can be selected for identification, and the texture on the surface of the touch subject can be identified as a real fingerprint or a fake fingerprint by judging whether the slope of the change curve formed by each grayscale value varies within the range of 2.1DN / μm to 3.2DN / μm.

[0051] In some embodiments, the texture on the surface of the touch body includes: valleys and ridges; the second preset change rule includes that in the central area of ​​the true fingerprint recognition image, the slope of the change curve formed by each grayscale value from the bottom of the valley to the top of the ridge is greater than the fifth preset slope and less than the sixth preset slope, and the width from the bottom of the valley to the top of the ridge in the central area is greater than the fifth preset width and less than the sixth preset width.

[0052] It should be noted that if Figure 3As shown, since there is a certain air gap between the valley and the mobile phone screen, and the refractive index of the air and the surface of the mobile phone are different, the light can be reflected at the boundary of the air gap formed by the mobile phone screen and the valley of the finger, and the corresponding valley top position can form a convergence effect on the light, resulting in the top of the valley having a stronger ability to reflect light, and the corresponding grayscale value in the recognition image is larger, and the position far from the top of the valley has a weaker ability to reflect light, and the corresponding grayscale value in the recognition image is smaller. The grayscale values ​​corresponding to the bottom of the valley in the central area of ​​the finger to the top of the ridge form a change curve, and the slope of the grayscale value change curve varies within a certain range, for example, the slope of the change curve varies between the fifth slope and the sixth slope, wherein the fifth slope can be 2.1DN / μm, and the sixth slope can be 3.2DN / μm. It should be noted here that the fifth slope and the sixth slope can be selected with the same values ​​as the third slope and the fourth slope mentioned above, because the real finger fingerprint is relatively symmetrical from ridge to valley and then from valley to ridge, and its slope will not be too different, and the same is true for the width. At the same time, the width from the bottom of the valley to the top of the ridge in the central area of ​​the recognition image also varies within a certain range. For example, the width from the bottom of the valley to the top of the ridge in the central area varies between the fifth preset width and the sixth preset width, wherein the fifth preset width may be 150 microns and the sixth preset width may be 300 microns. In practical applications, the grayscale values ​​of the pixels between 150 microns and 300 microns in the central area of ​​the recognition image may be selected, and the slope of the change curve formed by each grayscale value may be determined to vary within the range of 2.1 DN / μm to 3.2 DN / μm to identify whether the lines on the surface of the touch subject are real fingerprints or fake fingerprints.

[0053] Embodiment 2

[0054] Figure 4 A schematic diagram of a display module provided in an embodiment of the present disclosure is shown in FIG. Figure 4 As shown, the display module includes: a substrate 401, a display panel 402 located on the substrate 401, and a plurality of image sensors 403 located between the substrate 401 and the display panel 402. The display module also includes: an image processor (not shown in the figure) connected to the image sensor 403; the image processor is used to generate an identification image according to a light signal reflected by the texture on the surface of the touch subject; determine a grayscale value variation rule of at least a part of the area in the identification image; and determine whether the texture on the surface of the touch subject is a real fingerprint or a fake fingerprint according to the grayscale value variation rule of at least a part of the area in the identification image.

[0055] It should be noted that in the display device provided in the embodiment of the present disclosure, the display panel 402 can display and emit light to the surface of the touch body. When the surface of the touch body contacts the display panel 402, the light can be reflected. The image sensor 403 can convert the reflected light signal into an electrical signal and input it into the image processor to generate an identification image. The image processor can identify whether the texture on the surface of the touch body is a fake fingerprint based on the change law of the grayscale value of at least part of the area in the identification image. This can effectively avoid the problem of using fake fingerprints to attack the fingerprint recognition system, thereby improving the security of the fingerprint recognition system and thus improving the user experience.

[0056] In some embodiments, Figure 4 As shown, the display module further includes: a collimating structure 404 located between the image sensor 403 and the display panel 402; the collimating structure 404 includes a fiber optic plate or a plurality of micro lenses arranged in an array.

[0057] It should be noted that the collimating structure 404 composed of a plurality of micro lenses arranged in an optical fiber plate or an array can collimate the light reflected from the surface of the touch body, thereby reducing the crosstalk between the protrusions and depressions on the surface of the touch body. In addition, the collimating structure 404 can also include an infrared filter layer to reduce the influence of external light on the reflected light.

[0058] In some embodiments, when the surface of the touch subject contacts the display panel 402 , the orthographic projection of the surface of the touch subject on the substrate 401 falls within the orthographic projections of the plurality of image sensors 403 on the substrate.

[0059] It should be noted that the area of ​​the region where the multiple image sensors 403 are located is larger than the area of ​​the touch body surface. In this way, the image sensor 403 can accurately identify the edge of the touch body surface, improve the accuracy of fingerprint recognition, and effectively avoid the problem of using fake fingerprints to attack the fingerprint recognition system. Therefore, the security of the fingerprint recognition system can be improved, thereby improving the user experience.

[0060] Embodiment 3

[0061] An embodiment of the present disclosure provides a display device, which includes a display module as provided in any of the above embodiments. The display device can be a mobile phone, a tablet computer, a laptop computer, a smart door lock, or other device with an optical fingerprint recognition function. The implementation principle is the same as the principle of the above display module and fingerprint recognition method, and will not be repeated here.

[0062] It is to be understood that the above embodiments are merely exemplary embodiments used to illustrate the principles of the present disclosure, but the present disclosure is not limited thereto. For those of ordinary skill in the art, various modifications and improvements can be made without departing from the spirit and substance of the present disclosure, and these modifications and improvements are also considered to be within the scope of protection of the present disclosure.

Claims

1. A fingerprint recognition method for identifying the texture of a touch subject surface, characterized in that: The fingerprint recognition method comprises: generating an identification image according to light signals reflected by the textures on the surface of the touch body; Determining a grayscale value variation rule of at least a portion of the identified image; According to the grayscale value variation rule of at least a part of the area in the recognition image, determining whether the texture on the surface of the touch subject is a real fingerprint or a fake fingerprint; The recognition image has a central area and an edge area surrounding the central area; and judging whether the texture on the surface of the touch subject is a real fingerprint or a fake fingerprint according to a grayscale value variation rule of at least a part of the area in the recognition image includes: Determine whether the grayscale value variation rule of the edge area of ​​the recognition image conforms to a first preset variation rule; the first preset variation rule is the grayscale value variation rule of the edge area of ​​the real fingerprint recognition image extracted by using a neural network model; If the grayscale value variation rule of the edge area of ​​the recognition image conforms to the first preset variation rule, it is determined that the texture on the surface of the touch subject is a true fingerprint; The first preset change rule includes that the slope of the change curve formed by each grayscale value in the edge area of ​​the true fingerprint recognition image is greater than the first preset slope and less than the second preset slope, and the width of the edge area is greater than the first preset width and less than the second preset width.

2. The fingerprint recognition method according to claim 1, characterized in that: The recognition image has a central area and an edge area surrounding the central area; judging whether the texture on the surface of the touch subject is a real fingerprint or a fake fingerprint according to a grayscale value variation rule of at least a part of the area in the recognition image, further comprising: Determine whether the grayscale value variation rule of the central area of ​​the recognition image conforms to a second preset variation rule; the second preset variation rule is the grayscale value variation rule of the central area of ​​the real fingerprint recognition image extracted by using a neural network model; If the grayscale value variation rule of the central area of ​​the recognition image conforms to the second preset variation rule, it is determined that the texture on the surface of the touch body is a true fingerprint.

3. The fingerprint recognition method according to claim 2, characterized in that: The texture on the surface of the touch body includes: valleys and ridges; the second preset change rule includes that in the central area of ​​the true fingerprint recognition image, the slope of the change curve formed by each grayscale value from the top of the ridge to the bottom of the valley is greater than the third preset slope and less than the fourth preset slope, and the width from the top of the ridge to the bottom of the valley in the central area is greater than the third preset width and less than the fourth preset width.

4. The fingerprint recognition method according to claim 2, characterized in that: The texture on the surface of the touch body includes: valleys and ridges; the second preset change rule includes that in the central area of ​​the true fingerprint recognition image, the slope of the change curve formed by each grayscale value from the bottom of the valley to the top of the ridge is greater than the fifth preset slope and less than the sixth preset slope, and the width from the bottom of the valley to the top of the ridge in the central area is greater than the fifth preset width and less than the sixth preset width.

5. A display module, comprising: A substrate, a display panel located on the substrate, and a plurality of image sensors located between the substrate and the display panel, wherein the display module further comprises: an image processor connected to the image sensor; the image processor is used to execute the fingerprint recognition method as described in any one of claims 1 to 4.

6. The display module according to claim 5, characterized in that: The display module further includes: a collimation structure located between the image sensor and the display panel; The collimating structure includes a fiber optic plate or a plurality of micro lenses arranged in an array.

7. The display module according to claim 5, characterized in that: When the surface of the touch body contacts the display panel, the orthographic projection of the surface of the touch body on the substrate falls within the orthographic projections of the plurality of image sensors on the substrate.

8. A display device, characterized in that: Comprising a display module as described in any one of claims 5-7.

Images