WO2021017014A1

WO2021017014A1 - Fingerprint recognition and anti-counterfeiting method and apparatus, and electronic device

Info

Publication number: WO2021017014A1
Application number: PCT/CN2019/098945
Authority: WO
Inventors: 蒋鹏
Original assignee: 深圳市汇顶科技股份有限公司
Priority date: 2019-08-01
Filing date: 2019-08-01
Publication date: 2021-02-04
Also published as: CN110582780A

Abstract

The embodiments of the present application relate to a fingerprint recognition and anti-counterfeiting method and apparatus, and an electronic device. The fingerprint recognition apparatus is arranged below a display screen of an electronic device, and a fingerprint detection area of the display screen comprises a central area and a surrounding area that do not overlap with each other. The fingerprint recognition apparatus comprises: a light path guiding structure for guiding a returned light signal to an optical sensor, wherein the returned light signal is a light signal returned after light emitted by a light-emitting display pixel in a fingerprint detection area irradiates a finger, a light-emitting display pixel in a central area emits monochromatic light to irradiate the finger, and a light-emitting display pixel in a surrounding area emits light of a plurality of colors distributed at intervals in terms of space to irradiate the finger; and the optical sensor for receiving a light signal passing through the optical path guiding structure, so as to acquire a fingerprint image of the finger, wherein a central part, corresponding to the central area, of the fingerprint image is used for fingerprint recognition, and a surrounding part, corresponding to the surrounding area, of the fingerprint image is used for fingerprint anti-counterfeiting authentication.

Description

Fingerprint identification and anti-counterfeiting method, device and electronic equipment

Technical field

This application relates to the field of biometric identification, and in particular to methods, devices and electronic equipment for fingerprint identification and anti-counterfeiting.

Background technique

With the gradual popularity of mobile phones with under-screen optical fingerprint solutions, higher requirements are put forward for the anti-counterfeiting of under-screen optical fingerprints. However, the currently available under-screen optical fingerprint technology has limited anti-counterfeiting functions, and most of them have almost no anti-counterfeiting functions.

For example, there are currently two main under-screen optical fingerprint sensor technologies. The first is an under-screen optical fingerprint recognition technology based on a periodic microhole array, which is susceptible to the influence of moiré fringes. The second is based on the integrated micro-lens under-screen optical fingerprint recognition technology. The under-screen optical fingerprint recognition technology of these two technologies extracts fingerprint information by illuminating all pixels of the fingerprint pressing area, and then performs fingerprint recognition, but this does not have a good degree of recognition for various real and fake fingers.

Summary of the invention

This application provides a method, device and electronic equipment for fingerprint identification and anti-counterfeiting, which can perform fingerprint identification and anti-counterfeiting authentication.

In a first aspect, a fingerprint identification device is provided, which is arranged under a display screen of an electronic device, the display screen includes a plurality of light-emitting display pixels, the display screen includes a fingerprint detection area, and the fingerprint detection area includes non-overlapping The fingerprint identification device includes a light path guiding structure for guiding the return light signal to the optical sensor, and the return light signal is the fingerprint detection The light emitted by the light-emitting display pixels in the area illuminates the finger and the returned light signal, wherein the light-emitting display pixels in the central area emit monochromatic light to illuminate the finger, and the light-emitting display pixels in the surrounding area emit spatially spaced signals. The distributed light of multiple colors illuminates the finger; an optical sensor is located below the light path guiding structure, and is used to receive light signals passing through the light path guiding structure, and the light signals are used to obtain fingerprint images of the finger The central part of the fingerprint image corresponding to the central area is used for fingerprint identification, and the surrounding part of the fingerprint image corresponding to the surrounding area is used for fingerprint anti-counterfeiting authentication.

With reference to the first aspect, in an implementation of the first aspect, the light emitted by the light-emitting display pixels in the surrounding area has a different color from the monochromatic light emitted by the light-emitting display pixels in the central area.

With reference to the first aspect and the foregoing implementation manners, in another implementation manner of the first aspect, the fingerprint detection area further includes a supplementary light area located at the periphery of the surrounding area, and the light-emitting display in the supplementary light area The pixels emit monochromatic light to illuminate the finger.

In combination with the first aspect and the foregoing implementation manners of the first aspect, in another implementation manner of the first aspect, the monochromatic light emitted by the light-emitting display pixels in the supplementary light area is compared with the single-color light emitted by the light-emitting display pixels in the central area. The colors of the shades are the same.

With reference to the first aspect and the foregoing implementation manners, in another implementation manner of the first aspect, the area of the central region is larger than the area of the surrounding region.

With reference to the first aspect and the foregoing implementation manners, in another implementation manner of the first aspect, the central area is rectangular or circular.

With reference to the first aspect and the foregoing implementation manners, in another implementation manner of the first aspect, the surrounding area includes multiple sets of sub-regions, and the light-emitting display pixels in the same set of sub-regions in the multiple sets of sub-regions emit the same Color light illuminates the finger, and light-emitting display pixels in different groups of sub-areas in the plurality of groups of sub-areas emit light of different colors to illuminate the finger.

With reference to the first aspect and the foregoing implementation manners of the first aspect, in another implementation manner of the first aspect, the subregions of different groups in the plurality of groups of subregions are arranged at intervals.

With reference to the first aspect and the foregoing implementation manners of the first aspect, in another implementation manner of the first aspect, the areas and/or shapes of multiple subregions in the same group of subregions in the multiple sets of subregions are the same.

With reference to the first aspect and the foregoing implementation manners of the first aspect, in another implementation manner of the first aspect, each subregion in the plurality of groups of subregions includes 5-10 light-emitting display pixels.

With reference to the first aspect and the foregoing implementation manners thereof, in another implementation manner of the first aspect, the multiple groups of sub-areas are two groups of sub-areas or three groups of sub-areas.

With reference to the first aspect and the foregoing implementation manners, in another implementation manner of the first aspect, the two sets of sub-regions include a first set of sub-regions and a second set of sub-regions. The area and shape of the sub-regions are the same as those of the sub-regions in the second group of sub-regions.

With reference to the first aspect and the foregoing implementation manners thereof, in another implementation manner of the first aspect, the shape of the subregions in the first group of subregions is the same as the shape of the subregions in the second set of subregions .

With reference to the first aspect and the foregoing implementation manners thereof, in another implementation manner of the first aspect, the shapes of the sub-regions in the first group of sub-regions and the second group of sub-regions are both square, circular, or Semicircle.

In combination with the first aspect and the foregoing implementation manners of the first aspect, in another implementation manner of the first aspect, the shape of the subregion in the first group of subregions is different from the shape of the subregion in the second set of subregions. the same.

With reference to the first aspect and the foregoing implementation manners of the first aspect, in another implementation manner of the first aspect, the shape of the subregions in the first group of subregions is square, and the shape of the subregions in the second set of subregions is square. The shape is round.

In combination with the first aspect and the foregoing implementation manners, in another implementation manner of the first aspect, the fingerprint identification device further includes: a filter, which is arranged above the optical sensor and is used to filter out the return light The infrared light signal in the signal.

With reference to the first aspect and the foregoing implementation manners thereof, in another implementation manner of the first aspect, the multiple sets of sub-regions include a third set of sub-regions, and the light-emitting display pixels in the third set of sub-regions are used to emit Red light; the filter is used to filter the light signal returned after the red light irradiates the finger.

With reference to the first aspect and the foregoing implementation manners, in another implementation manner of the first aspect, the light path guiding structure includes an optical lens; or, the light path guiding structure includes a plurality of collimating units or microhole arrays. An optical collimator, the optical collimator is used to transmit the return light signal to the corresponding optical sensing unit in the sensing array of the optical sensor through the plurality of collimating units or microhole arrays; or The optical path guiding structure includes a microlens array with a plurality of microlenses and a light blocking layer with a plurality of microholes, and the microlens array is used to focus the return light signals to the microlenses respectively. The micro-holes corresponding to the light blocking layer are transmitted to the corresponding optical sensing units in the sensing array of the optical sensor through the micro-holes.

Combining the first aspect and the foregoing implementation manners thereof, in another implementation manner of the first aspect, the monochromatic light emitted by the light-emitting display pixels in the central area is green light or cyan light, and the luminescence in the surrounding area is The display pixels emit light of multiple colors including at least two of red light, blue light, yellow light, and black light.

In combination with the first aspect and the foregoing implementation manners, in another implementation manner of the first aspect, the surrounding part in the fingerprint image is used to determine whether the fingerprint image to be detected is a real finger based on a deep learning algorithm Fingerprint image.

Combining the first aspect and the foregoing implementation manners thereof, in another implementation manner of the first aspect, the deep learning algorithm includes at least one of the following: support vector machine, convolutional neural network, recurrent neural network, and k-means clustering algorithm.

Therefore, the fingerprint identification device of the embodiment of the present application is arranged under the display screen of the electronic device, and the display screen includes a fingerprint detection area. The central area of the fingerprint detection area is set to illuminate the finger in a single color, and the surrounding area is set to illuminate the finger with a color pattern. This edge pattern can be a periodic grid, or a pattern with a certain curvature on the edge, or multiple color lines, so that the acquired fingerprint image can be used for fingerprint recognition and fingerprint anti-counterfeiting authentication, which solves the existing problem. The under-screen optical fingerprint recognition device cannot prevent the problem of false fingerprints in various forms, and improves the security level of the system, thereby enhancing the user experience. In addition, the cost of the optical fingerprint module using the color patterning method of the present application is much lower than that of the color filter fingerprint module; moreover, the optical sensor chip in the embodiment of the present application has a shorter processing cycle, lower cost, and higher yield. high.

In a second aspect, an electronic device is provided. The electronic device includes a fingerprint identification device, a display screen, and a processor as in the first aspect or any possible implementation of the first aspect. The display screen includes a plurality of light emitting devices. Display pixels, the light-emitting display pixels are used to display images, the display screen includes a fingerprint detection area, the fingerprint detection area includes a central area and a surrounding area that do not overlap each other, the central area is located in the middle of the surrounding area, the The light-emitting display pixels in the central area emit monochromatic light to illuminate the finger, and the light-emitting display pixels in the surrounding area emit light of multiple colors distributed at intervals to illuminate the finger; the processor is used to illuminate the finger according to the fingerprint The light signal received by the optical sensor in the recognition device generates a fingerprint image, and performs fingerprint recognition on the finger according to the central part of the fingerprint image corresponding to the central area, and according to the fingerprint image and the The surrounding part corresponding to the surrounding area performs fingerprint anti-counterfeiting authentication on the finger.

With reference to the second aspect, in an implementation manner of the second aspect, the processor is further configured to: based on a deep learning algorithm, determine the fingerprint image to be detected according to the surrounding part in the fingerprint image to be detected Whether it is a fingerprint image of a real finger.

Combining the second aspect and the foregoing implementation manners thereof, in another implementation manner of the second aspect, the processor is further configured to: based on a deep learning algorithm, according to the distribution image of the reflected light signal in the surrounding part and/or The distribution image of the scattered light signal to determine whether the fingerprint image to be detected is a fingerprint image of a real finger, wherein the reflected light signal is the light emitted by the light-emitting display pixels in the surrounding area generated on the surface of the target finger The returned light signal after reflection, and the scattered light signal is the light signal returned after the light emitted by the light-emitting display pixels in the surrounding area is scattered inside the target finger.

In combination with the second aspect and the foregoing implementation manners, in another implementation manner of the second aspect, the processor is further configured to: based on a deep learning algorithm, according to the distribution image and/or the first optical signal in the surrounding part Or the distribution image of the second light signal to determine whether the fingerprint image to be detected is a fingerprint image of a real finger, wherein the first light signal and the second light signal are respectively the light-emitting display pixels in the surrounding area Light signals of any two colors of the emitted light of multiple colors after irradiating the target finger.

With reference to the second aspect and the foregoing implementation manners of the second aspect, in another implementation manner of the second aspect, the processor is further configured to: determine the distribution image of the first optical signal in the surrounding part and the second The distribution image of the light signal, the first light signal is the light signal returned by the blue light emitted by the light-emitting display pixels in the surrounding area after irradiating the target finger, and the second light signal is the light signal in the surrounding area The red light emitted by the luminescent display pixel returns the optical signal after irradiating the target finger; based on the deep learning algorithm, according to the difference between the distribution image of the first optical signal and the distribution image of the second optical signal, determine Whether the fingerprint image to be detected is a fingerprint image of a real finger.

In combination with the second aspect and the foregoing implementation manners of the second aspect, in another implementation manner of the second aspect, the processor is further configured to: obtain several sample data, the several sample data including several real finger data and several fake finger data The plurality of real finger data includes the surrounding parts corresponding to the surrounding area in the fingerprint image obtained when a plurality of real fingers touch the fingerprint detection area, and the plurality of fake finger data includes a plurality of fake fingers touching the surrounding area. The surrounding part of the fingerprint image obtained during the fingerprint detection area corresponding to the surrounding area; training based on the several sample data to obtain a deep learning model of fingerprint images of real and fake fingers; according to the deep learning model, according to The surrounding part of the fingerprint image to be detected is determined whether the fingerprint image to be detected is a fingerprint image of a real finger.

In combination with the second aspect and the foregoing implementation manners, in another implementation manner of the second aspect, the deep learning algorithm includes at least one of the following: support vector machine, convolutional neural network, recurrent neural network, and k-means clustering algorithm.

Therefore, the electronic device of the embodiment of the present application has an under-screen fingerprint identification device. The display screen of the electronic device includes a fingerprint detection area. A monochrome illuminating finger is set in the center area of the fingerprint detection area, and a color pattern is set to illuminate the finger in the surrounding area. The edge pattern can be a periodic grid, or a pattern with a certain curvature on the edge, or multiple colored lines, so that the acquired fingerprint image can be used for fingerprint recognition and fingerprint anti-counterfeiting authentication, which solves the problem of existing screens. The lower optical fingerprint recognition device cannot prevent the problem of false fingerprints in various forms, and improves the security level of the system, thereby enhancing the user experience. In addition, the cost of the optical fingerprint module using the color patterning method of the present application is much lower than that of the color filter fingerprint module.

In a third aspect, a fingerprint identification and anti-counterfeiting method is provided, the method comprising: acquiring a fingerprint image of a target finger to be detected, where the fingerprint image to be detected is the fingerprint of the target finger touching the fingerprint detection area of the display screen Image, the fingerprint detection area includes a non-overlapping central area and a surrounding area, the central area is located in the middle of the surrounding area, the light-emitting display pixels in the central area emit monochromatic light to illuminate the target finger, so The light-emitting display pixels in the surrounding area emit light of multiple colors to illuminate the target finger; perform fingerprint recognition on the target finger according to the central part of the fingerprint image to be detected corresponding to the central area; Perform fingerprint anti-counterfeiting authentication on the target finger in the surrounding part corresponding to the surrounding area in the fingerprint image to be detected.

With reference to the third aspect, in an implementation manner of the third aspect, the performing fingerprint anti-counterfeiting authentication on the target finger according to the surrounding part corresponding to the surrounding area in the fingerprint image to be detected includes: depth-based The learning algorithm determines whether the fingerprint image to be detected is a fingerprint image of a real finger according to the surrounding part in the fingerprint image to be detected.

Combining the third aspect and the foregoing implementation manners thereof, in another implementation manner of the third aspect, the deep learning algorithm is used to determine the fingerprint image to be detected according to the surrounding part in the fingerprint image to be detected Whether it is a fingerprint image of a real finger, including: based on a deep learning algorithm, determining whether the fingerprint image to be detected is a fingerprint of a real finger according to the distribution image of the reflected light signal and/or the distribution image of the scattered light signal in the surrounding part An image, wherein the reflected light signal is the light signal returned by the light emitted by the light-emitting display pixels in the surrounding area after being reflected on the surface of the target finger, and the scattered light signal is the light emission in the surrounding area The light emitted by the display pixel is scattered inside the target finger and then returned to the light signal.

Combining the third aspect and the foregoing implementation manners thereof, in another implementation manner of the third aspect, the deep learning algorithm is used to determine the fingerprint image to be detected according to the surrounding part in the fingerprint image to be detected Whether it is a fingerprint image of a real finger, including: based on a deep learning algorithm, determining whether the fingerprint image to be detected is a real finger according to the distribution image of the first light signal and/or the distribution image of the second light signal in the surrounding part The fingerprint image of the fingerprint image, wherein the first light signal and the second light signal are respectively the light of any two colors of the multiple colors emitted by the light-emitting display pixels in the surrounding area illuminating the target finger After returning the light signal.

Combining the third aspect and the foregoing implementation manners thereof, in another implementation manner of the third aspect, the deep learning algorithm is used according to the distribution image of the first optical signal and/or the second optical signal in the surrounding part A distribution image, determining whether the fingerprint image to be detected is a fingerprint image of a real finger, including: determining a distribution image of the first light signal and a distribution image of the second light signal in the surrounding part, the first The light signal is the light signal returned by the blue light emitted by the light-emitting display pixels in the surrounding area after irradiating the target finger, and the second light signal is the red light emitted by the light-emitting display pixels in the surrounding area. The optical signal returned after the target finger; based on a deep learning algorithm, determine whether the fingerprint image to be detected is a real finger based on the difference between the distribution image of the first optical signal and the distribution image of the second optical signal Fingerprint image.

Combining the third aspect and the foregoing implementation manners thereof, in another implementation manner of the third aspect, the deep learning algorithm is used to determine the fingerprint image to be detected according to the surrounding part in the fingerprint image to be detected Whether it is a fingerprint image of a real finger, including: acquiring a number of sample data including a number of real finger data and a number of fake finger data, the number of real finger data including a number of real fingers touching the fingerprint detection area Surrounding parts in the acquired fingerprint image corresponding to the surrounding area, and the plurality of fake finger data includes the surrounding parts corresponding to the surrounding area in the fingerprint image obtained when the fake fingers touch the fingerprint detection area; The several sample data are trained to obtain a deep learning model of fingerprint images of real and fake fingers; according to the deep learning model, according to the surrounding part of the fingerprint image to be detected, it is determined whether the fingerprint image to be detected is The fingerprint image of a real finger.

With reference to the third aspect and the foregoing implementation manners, in another implementation manner of the third aspect, the deep learning algorithm includes at least one of the following: support vector machine, convolutional neural network, recurrent neural network, and k-means clustering algorithm.

Therefore, the under-screen fingerprint identification and anti-counterfeiting method of the embodiment of the present application is suitable for electronic equipment with under-screen fingerprint identification devices. The display screen of the electronic equipment includes a fingerprint detection area, and a single color is set in the center area of the fingerprint detection area. Illuminate the finger and set a color pattern in the surrounding area to illuminate the finger. This edge pattern can be a periodic grid, or a pattern with a certain curvature on the edge, or multiple colored lines, so that the acquired fingerprint image can be fingerprinted. , Fingerprint anti-counterfeiting authentication can also be performed, which solves the problem that the existing under-screen optical fingerprint recognition device cannot prevent various forms of fake fingerprints, improves the security level of the system, and thereby enhances the user experience. In addition, the cost of the optical fingerprint module using the color patterning method of the present application is much lower than that of the color filter fingerprint module; moreover, the optical sensor chip of the embodiment of the present application has a shorter processing cycle, lower cost, and higher yield. .

In a fourth aspect, an electronic device is provided, including: a storage unit and a processor, the storage unit is used to store instructions, the processor is used to execute the instructions stored in the memory, and when the processor executes the instructions stored in the memory The execution causes the processor to execute the third aspect or the method in any possible implementation manner of the third aspect.

In a fifth aspect, a computer-readable medium is provided for storing a computer program, and the computer program includes instructions for executing the third aspect or any possible implementation of the third aspect.

In a sixth aspect, a computer program product including instructions is provided. When the computer runs the finger of the computer program product, the computer executes the fingerprint in the third aspect or any possible implementation of the third aspect. Methods of identification and anti-counterfeiting. Specifically, the computer program product can run on the electronic device of the fourth aspect.

Description of the drawings

Fig. 1 is a schematic diagram of an electronic device according to an embodiment of the present application.

Fig. 2 is another schematic diagram of an electronic device according to an embodiment of the present application.

Fig. 3 is a partial schematic diagram of another electronic device according to an embodiment of the present application.

Fig. 4 is a schematic diagram of a fingerprint detection area according to an embodiment of the present application.

Fig. 5 is another schematic diagram of a fingerprint detection area according to an embodiment of the present application.

Fig. 6 is another schematic diagram of a fingerprint detection area according to an embodiment of the present application.

Fig. 7 is another schematic diagram of a fingerprint detection area according to an embodiment of the present application.

Fig. 8 is another schematic diagram of a fingerprint detection area according to an embodiment of the present application.

Fig. 9 is another schematic diagram of a fingerprint detection area according to an embodiment of the present application.

Fig. 10 is another schematic diagram of a fingerprint detection area according to an embodiment of the present application.

Fig. 11 is a schematic flowchart of an off-screen fingerprint identification and anti-counterfeiting method according to an embodiment of the present application.

Detailed ways

The technical solutions in the embodiments of the present application will be described below in conjunction with the drawings.

It should be understood that the embodiments of this application can be applied to optical fingerprint systems, including but not limited to optical fingerprint identification systems and medical diagnostic products based on optical fingerprint imaging. The embodiments of this application only take optical fingerprint systems as an example for description, but should not The embodiments of the application constitute any limitation, and the embodiments of the present application are also applicable to other systems using optical imaging technology.

As a common application scenario, the optical fingerprint system provided in the embodiments of this application can be applied to smart phones, tablet computers, and other mobile terminals with display screens or other electronic devices; more specifically, in the above electronic devices, fingerprint identification The device may specifically be an optical fingerprint device, which may be arranged in a partial area or an entire area under the display screen, thereby forming an under-display optical fingerprint system. Alternatively, the fingerprint identification device may be partially or fully integrated into the display screen of the electronic device, thereby forming an in-display optical fingerprint system.

FIG. 1 and FIG. 2 are schematic diagrams of the structure of an electronic device to which the embodiment of the application can be applied. FIG. 1 is a front view of the electronic device, and FIG. 2 is a side view of the electronic device. As shown in FIGS. 1 and 2, the electronic device 10 includes a display screen 120 and an optical fingerprint device 130, wherein the optical fingerprint device 130 is arranged in a partial area below the display screen 120. The optical fingerprint device 130 includes an optical fingerprint sensor, and the optical fingerprint sensor includes a sensing array 133 with a plurality of optical sensing units 131, and the area where the sensing array is located or its sensing area is the fingerprint detection area 103 of the optical fingerprint device 130. As shown in FIG. 1, the fingerprint detection area 103 is located in the display area of the display screen 120. In an alternative embodiment, the optical fingerprint device 130 can also be arranged in other positions, such as the side of the display screen 120 or the non-transmissive area on the edge of the electronic device 10, and the optical fingerprint device 130 can be designed through the optical path. At least part of the optical signal of the display area is guided to the optical fingerprint device 130, so that the fingerprint detection area 103 is actually located in the display area of the display screen 120.

It should be understood that the area of the fingerprint detection area 103 may be different from the area of the sensing array of the optical fingerprint device 130. For example, through the optical path design of lens imaging, the reflective folding optical path design, or other optical path design such as light convergence or reflection, it can make The area of the fingerprint detection area 103 of the optical fingerprint device 130 is larger than the area of the sensing array of the optical fingerprint device 130. In other alternative implementations, if for example, light collimation is used for light path guidance, the fingerprint detection area 103 of the optical fingerprint device 130 can also be designed to be substantially the same as the area of the sensing array of the optical fingerprint device 130.

Therefore, when the user needs to unlock the electronic device 10 or perform other fingerprint verification, he only needs to press his finger on the fingerprint detection area 103 located on the display screen 120 to realize fingerprint input. Since fingerprint detection can be implemented in the screen, the electronic device 10 adopting the above structure does not need to reserve space on the front side to set fingerprint buttons (such as the Home button), so that a full screen solution can be adopted, that is, the display area of the display screen 120 can be It basically extends to the front of the entire electronic device 10.

As an optional implementation, as shown in FIG. 2, the optical fingerprint device 130 includes a light detecting part 134 and an optical component 132, and the light detecting part 134 includes the sensing array and a reader electrically connected to the sensing array. The circuit and other auxiliary circuits can be fabricated on a chip (Die) through a semiconductor process, such as an optical imaging chip or an optical fingerprint sensor. The sensing array is specifically a photodetector array, which includes a plurality of arrays. Distributed photodetector, the photodetector can be used as the above-mentioned optical sensing unit; the optical component 132 can be arranged above the sensing array of the light detection part 134, which can specifically include a filter layer (Filter), light guide The light guide layer or light path guiding structure and other optical elements, the filter layer can be used to filter the ambient light penetrating the finger, and the light guide layer or light path guiding structure is mainly used to guide the reflected light reflected from the finger surface to the The sensing array performs optical inspection.

In terms of specific implementation, the optical assembly 132 and the light detecting part 134 may be packaged in the same optical fingerprint component. For example, the optical component 132 and the optical detection part 134 can be packaged in the same optical fingerprint chip, or the optical component 132 can be arranged outside the chip where the optical detection part 134 is located, for example, the optical component 132 can be attached to the Above the chip, or part of the components of the optical assembly 132 are integrated in the above chip.

Among them, the light guide layer or light path guiding structure of the optical component 132 has multiple implementation schemes. For example, the light guide layer may specifically be a collimator layer made on a semiconductor silicon wafer, which has multiple collimators. A collimating unit or a micro-hole array, the collimating unit can be specifically a through hole or a small hole. Among the reflected light reflected from the finger, the light that is perpendicularly incident on the collimating unit can pass through and be received by the optical sensor unit below it , And the light with too large incident angle is attenuated by multiple reflections inside the collimating unit. Therefore, each optical sensing unit can basically only receive the reflected light reflected by the fingerprint pattern directly above it, so the sensing array is The fingerprint image of the finger can be detected.

In another embodiment, the light guide layer or the light path guide structure can also be an optical lens (Lens) layer, which has one or more lens units, such as a lens group composed of one or more aspheric lenses, The reflected light reflected from the finger is condensed to the sensing array of the light detection part 134 below it, so that the sensing array can perform imaging based on the reflected light, thereby obtaining a fingerprint image of the finger. Optionally, the optical lens layer may further have a pinhole formed in the optical path of the lens unit, and the pinhole may cooperate with the optical lens layer to expand the field of view of the optical fingerprint device, so as to improve the fingerprint imaging of the optical fingerprint device 130 effect.

In other embodiments, the light guide layer or the light path guide structure may also specifically adopt a micro-lens (Micro-Lens) layer. The micro-lens layer has a micro-lens array formed by a plurality of micro-lens, which may be formed by a semiconductor growth process or Other processes are formed above the sensing array of the light detection part 134, and each microlens can correspond to one of the sensing units of the sensing array. In addition, other optical film layers may be formed between the microlens layer and the sensing unit, such as a dielectric layer or a passivation layer. More specifically, a barrier with microholes may also be formed between the microlens layer and the sensing unit. Optical layer, wherein the micro-hole is formed between the corresponding micro lens and the sensing unit, the light blocking layer can block the optical interference between the adjacent micro lens and the sensing unit, and allow the light corresponding to the sensing unit to pass through the The micro lens is converged into the micro hole and is transmitted to the sensing unit through the micro hole to perform optical fingerprint imaging. It should be understood that several implementation solutions of the above-mentioned light path guiding structure can be used alone or in combination. For example, a microlens layer can be further provided under the collimator layer or the optical lens layer. Of course, when the collimator layer or the optical lens layer is used in combination with the microlens layer, the specific laminated structure or optical path may need to be adjusted according to actual needs.

As an optional embodiment, the display screen 120 may be a display screen with a self-luminous display unit, such as an organic light-emitting diode (Organic Light-Emitting Diode, OLED) display screen or a micro-LED (Micro-LED) display screen . Taking an OLED display screen as an example, the optical fingerprint device 130 can use the display unit (ie, an OLED light source) of the OLED display screen 120 located in the fingerprint detection area 103 as an excitation light source for optical fingerprint detection. When the finger 140 is pressed on the fingerprint detection area 103, the display screen 120 emits a beam of light 111 to the target finger 140 above the fingerprint detection area 103. The light 111 is reflected on the surface of the finger 140 to form reflected light or passes through the finger 140. Internal scattering forms scattered light. For ease of description, in the embodiments of the present application, the above-mentioned reflected light and scattered light are collectively referred to as return light passing through the finger. Since the ridge and valley of the fingerprint have different ability to reflect, scatter or absorb light, the return light 151 from the fingerprint ridge and the return light 152 from the fingerprint ridge have different light intensities, and the return light passes through After the optical component 132, it is received by the sensor array 134 in the optical fingerprint device 130 and converted into a corresponding electrical signal, that is, a fingerprint detection signal; based on the fingerprint detection signal, fingerprint image data can be obtained, and fingerprint matching verification can be further performed. Thus, the electronic device 10 realizes the optical fingerprint recognition function.

It should be understood that, in specific implementation, the electronic device 10 further includes a transparent protective cover, which may be a glass cover or a sapphire cover, which is located above the display screen 120 and covers the front of the electronic device 10. . Therefore, in the embodiments of the present application, the so-called finger pressing on the display screen 120 actually refers to pressing on the cover plate above the display screen 120 or covering the surface of the protective layer of the cover plate.

On the other hand, in some embodiments, the optical fingerprint device 130 may only include one optical fingerprint sensor. At this time, the fingerprint detection area 103 of the optical fingerprint device 130 has a small area and a fixed position. Therefore, when the user performs fingerprint input It is necessary to press the finger to a specific position of the fingerprint detection area 103, otherwise the optical fingerprint device 130 may not be able to collect fingerprint images, resulting in poor user experience. In other alternative embodiments, the optical fingerprint device 130 may specifically include a plurality of optical fingerprint sensors; the plurality of optical fingerprint sensors may be arranged side by side under the display screen 120 in a splicing manner, and the sensing of the plurality of optical fingerprint sensors The areas collectively constitute the fingerprint detection area 103 of the optical fingerprint device 130. In other words, the fingerprint detection area 103 of the optical fingerprint device 130 may include multiple sub-areas, and each sub-area corresponds to the sensing area of one of the optical fingerprint sensors, so that the fingerprint collection area 103 of the optical fingerprint module 130 can be It extends to the main area of the lower half of the display screen, that is, extends to the area where the finger is habitually pressed, so as to realize the blind fingerprint input operation. Alternatively, when the number of optical fingerprint sensors is sufficient, the fingerprint detection area 130 can also be extended to half of the display area or even the entire display area, thereby realizing half-screen or full-screen fingerprint detection.

To sum up, the current under-screen optical fingerprint device usually includes a periodic small hole optical path solution and a macro lens solution according to the different light path guiding structure it includes. Both of these solutions place the optical fingerprint device on Below the display, for example, the way is below the OLED screen. When the finger is placed above the OLED of the bright screen, the finger will scatter or reflect the light emitted by the OLED screen, and the returning light from the finger will penetrate the OLED screen to the optical fingerprint device below the OLED. The fingerprint is a diffuse reflector, and the light returned by the finger may exist in all directions. The first periodic small hole solution (or collimator solution) is to collect the light leaked from the fingerprint screen through periodic small holes under the OLED screen. This part of the light contains the fingerprint signal and the internal structure signal of the screen. The second macro lens solution (including the optical lens solution) uses a macro lens to collect the light leaked from the OLED screen, and then detect fingerprints.

The lighting method of the under-screen optical fingerprint device that has been released generally uses a partial area monochrome pattern, which will light up all the pixels in the fingerprint detection area or fingerprint pressing area. This method can better reflect the fingerprint information of the finger, but because the full-area lighting basically reflects the boundary conditions between the glass cover on the surface of the screen and the fingerprint contact surface, this method has a poor anti-counterfeiting effect on true and false fingerprints. , So it cannot distinguish between true and false fingerprints.

The existing anti-counterfeiting solution generally involves fabricating color filters in a specific area of a Complementary Metal-Oxide-Semiconductor (CMOS) image sensor, and identifying true and false fingerprints through a deep learning method. However, the cost of such a color filter anti-counterfeiting solution is much higher than that of a non-filter solution.

Therefore, the embodiments of the present application propose a fingerprint identification and anti-counterfeiting method, device, and electronic equipment, which can perform fingerprint recognition and fingerprint anti-counterfeiting authentication, with lower cost and higher efficiency.

FIG. 3 shows a partial schematic diagram of an electronic device 20 according to an embodiment of the present application, and FIG. 3 is a side view of the electronic device 20. As shown in FIG. 3, the electronic device 20 includes a display screen 200 and a fingerprint identification device 300, and the display screen 200 is located above the fingerprint identification device 300.

Specifically, the display screen 200 may correspond to the display screen 120 in the electronic device 10 described in FIG. 1 and FIG. 2, and is suitable for the related description of the display screen 120 described above. For the sake of brevity, details are not repeated here.

Specifically, as shown in 3, the display screen 200 includes a number of light-emitting display pixels, which can be used to display images. The display screen 200 in FIG. 3 may represent a part of the display screen 200 instead of the actual size and size of the display 200. As shown in FIG. 3, the display screen 200 includes a fingerprint detection area 210 for finger pressing, that is, when the user needs to unlock the electronic device 20 or other fingerprint recognition, he only needs to press his finger on the fingerprint detection area 210, the fingerprint input can be realized. Wherein, the fingerprint detection area 210 may correspond to the fingerprint detection area 103 in the electronic device 10 described in FIG. 1 and FIG. 2, and is applicable to the relevant description of the fingerprint detection area 103 described above. For the sake of brevity, it will not be repeated here.

In addition, as shown in FIG. 3, the fingerprint detection area 210 includes a central area 211 and a surrounding area 212 that do not overlap each other, and the central area 211 is located in the middle of the surrounding area 212. The light-emitting display pixels in the central area 211 emit monochromatic light to illuminate the finger above it, and the light-emitting display pixels in the surrounding area 212 emit light of multiple colors distributed at intervals to illuminate the finger. That is, when a finger touches the fingerprint detection area 210, the central area 211 of the fingerprint detection area 210 illuminates the finger with monochromatic light, and the surrounding area 212 of the fingerprint detection area 210 illuminates the finger with a color pattern.

Specifically, after the light emitted by the light-emitting display pixels in the fingerprint detection area 210 irradiates the finger, a return light signal will be generated. Among them, the return light signal includes the light that returns after being reflected on the surface of the finger, as shown in the three groups of hollow arrow symbols in Figure 3; in addition, the return light signal also includes the light that returns after being scattered inside the finger, as shown in Figure 3. The three groups of black solid thick arrow symbols are shown.

It should be understood that the fingerprint identification device 300 is provided under the display screen 200 of the terminal device 20 in the embodiment of the present application, and the fingerprint identification device 300 may be used to receive the return light signal of the finger. Specifically, the fingerprint identification device 300 includes: an optical path guiding structure 310 and an optical sensor 320, and the optical sensor 320 is disposed under the optical path guiding structure 310. Wherein, the light path guiding structure 310 is used to: guide the return light signal to the optical sensor, the return light signal is the light signal returned after the light emitted by the light-emitting display pixel in the fingerprint detection area irradiates the finger; the optical sensor 320 is used for : Receive the light signal passing through the optical path guiding structure, the light signal is used to obtain the fingerprint image of the finger, the central part of the fingerprint image corresponding to the central area is used for fingerprint identification, and the fingerprint image corresponds to the surrounding area The surrounding part is used for fingerprint anti-counterfeiting authentication.

It should be understood that the optical path guiding structure 310 may correspond to the optical component 132 in the electronic device 10 described in FIGS. 1 and 2, and is suitable for the above-mentioned related description of the optical component 132; similarly, the optical sensor 320 may correspond to the above The optical fingerprint sensor in the electronic device 10 described in FIGS. 1 and 2, specifically, the optical sensor 320 may be the light detecting portion 134 in the above-mentioned electronic device 10, which is applicable to the above-mentioned related description about the light detecting portion 134, in order to It's concise, so I won't repeat it here.

For example, the optical path guiding structure 320 of the embodiment of the present application may include an optical lens.

For another example, the optical path guiding structure 320 of the embodiment of the present application may further include an optical collimator having a plurality of collimating units or a microhole array, and the optical collimator is used to pass the return optical signal through the plurality of collimating units Or the microhole array is respectively transmitted to the corresponding optical sensing unit in the sensing array of the optical sensor.

For another example, the optical path guiding structure 320 of the embodiment of the present application includes a microlens array with a plurality of microlenses and a light blocking layer with a plurality of microholes, and the microlens array is used to pass the return light signal through the plurality of microlenses. The lenses are respectively focused on the micro holes corresponding to the light blocking layer, and are transmitted to the corresponding optical sensing units in the sensing array of the optical sensor through the micro holes.

Therefore, considering that the material, spectrum, and internal optical scattering characteristics of fake fingerprints are far different from those of real fingers, in order to distinguish fingerprint images of real and fake fingers and improve the anti-counterfeiting ability of optical fingerprints under the screen, an embodiment of the present application proposes The method of using the edge area to emit colored light separately to realize the anti-counterfeiting authentication of optical fingerprints can be used for fingerprint identification and anti-counterfeiting of true and false fingerprints at the same time, which improves the user experience.

The following will describe in detail the light-emitting or lighting method of the fingerprint detection area and the method of fingerprint identification and anti-counterfeiting in the embodiment of the present application with reference to FIGS. 4 to 10.

FIG. 4 shows a schematic diagram of a fingerprint detection area 210 according to an embodiment of the present application. As shown in FIG. 4, the fingerprint detection area 210 includes a central area 211 and a surrounding area 212. The central area 211 is the central part of the fingerprint detection area 210, that is, the white area in the middle of FIG. 4. The light-emitting display pixels in the central area 211 emit monochromatic light to illuminate the finger, and the return light after the monochromatic light illuminates the finger passes through After the optical path guide structure is received by the optical sensor, the fingerprint image is obtained by this, and this part of the fingerprint image can be used for fingerprint identification.

Optionally, the light-emitting display pixels in the central area 211 can be used to emit monochromatic light for fingerprint recognition, where the monochromatic light can be light of any color. For example, the monochromatic light may be green light, cyan light or white light, and the embodiment of the present application is not limited thereto.

It should be understood that any light-emitting display pixel in the embodiments of the present application may refer to a combination of three colors of red, green, and blue. Therefore, each pixel may be used to emit light of various colors.

As shown in FIG. 4, the periphery of the central area 211 is the surrounding area 212, that is, the surrounding area 212 is located at the periphery of the middle white area in FIG. 4, which refers to the area with pattern filling in FIG. The peripheral area 212 surrounds the central area 212. The light-emitting display pixels in the peripheral area 212 emit light of multiple colors to illuminate the finger, and the lights of multiple colors are distributed at intervals in space. The return light after the light irradiates the finger is guided by the optical path. After the structure is received, the optical sensor obtains the corresponding image. This part of the image can be used for finger anti-counterfeiting authentication, that is, to confirm whether the finger is a real finger or a fake finger.

Optionally, the light-emitting display pixels in the surrounding area 212 may be used to emit light of multiple colors, and the light of multiple colors may be lights of any two or more colors. For example, the light of the multiple colors may include at least two of red light, blue light, green light, yellow light, and black light, where the black light means no light is emitted. In order to make the subsequent fingerprint anti-counterfeiting authentication effect better, usually choose light with a large color difference, which can maximize the spectral difference between true and false fingerprints.

It should be understood that if a finger touches the fingerprint detection area 210, the fingerprint image of the finger can be correspondingly obtained. Since the fingerprint detection area 210 is divided into a central area 211 and a surrounding area 212, and the light of the central area 211 and the surrounding area 211 are different, the corresponding The acquired fingerprint image of the finger can also be seen as two parts. For ease of description, the two parts are referred to as the central part and the surrounding part of the fingerprint image below. Among them, the fingerprint image corresponding to the central area 211 is the central part, the central part is obtained according to the return light signal generated by the monochromatic light emitted in the central area 211 irradiating the finger, and the central part is used for fingerprint identification to determine the Whether the fingerprint image is a pre-stored fingerprint image; in addition, the surrounding area 212 corresponds to the surrounding area in the fingerprint image, and the surrounding area is obtained based on the return light signal generated by irradiating the finger with multiple colors of light emitted by the surrounding area 212. The surrounding part is used for fingerprint anti-counterfeiting verification, that is, to determine whether the fingerprint image is a fingerprint image of a real finger, that is, to determine whether the finger touching the fingerprint detection area 210 is a real finger.

Since the central part of the fingerprint image is used for fingerprint identification, in order to ensure the accuracy of the central part of the fingerprint image of the obtained finger during fingerprint identification, that is, to ensure the clarity and accuracy of the fingerprint in the central part, it is necessary to use The central part is not less than a certain threshold, and correspondingly, it is necessary to set the central area 211 in the fingerprint detection area 210 to be no less than a certain threshold. Therefore, the area and shape of the central area 211 can be set according to actual application requirements.

For example, the area of the central area 211 may be set to be greater than the area of the surrounding area 212. In practical applications, the central area 211 can usually be set as a single connected area with an area greater than or equal to 16 mm ² , for example, considering the effect and cost, the central area 211 can be set as a rectangle of 5.5 mm * 8.5 mm; correspondingly, The peripheral area 212 may be set as an outer ring area with a width of 0.05 mm-3 mm at the edge of the central area 211. For another example, for the shape of the central area 211, the central area 211 may be set to be a rectangle or a circle. For example, in FIG. 4, the central area 211 is a rectangle as an example, but the embodiment of the present application is not limited to this.

Optionally, considering that the surrounding area 212 is usually small, in order to achieve a better lighting effect, a supplemental light area may also be set. FIG. 5 shows a schematic diagram of another fingerprint detection area 210 according to an embodiment of the present application. As shown in FIG. 5, compared with FIG. 4, it can be seen that the fingerprint detection area 210 includes a central area 211 and a surrounding area 212. The fingerprint detection area 210 may also include a supplementary light area 213 located at the periphery of the surrounding area 212, as shown in FIG. 4 In the outermost white area, the light-emitting display pixels in the supplemental light area 213 emit monochromatic light to illuminate the finger.

Optionally, the color of the monochromatic light emitted by the light-emitting display pixels in the supplemental light area 213 may be the same as or different from the color of the monochromatic light emitted by the light-emitting display pixels in the central area 211. Considering the effect of lighting, the monochromatic light emitted by the light-emitting display pixels in the supplemental light area 213 is usually set to be the same color as the monochromatic light emitted by the light-emitting display pixels in the central area 211.

In addition, the light of multiple colors emitted by the light-emitting display pixels in the surrounding area 212 may have the same color as the monochromatic light emitted by the light-emitting display pixels in the central area 211, or there may be no light of the same color. Considering the effect, the light of multiple colors emitted by the light-emitting display pixels in the surrounding area 212 is usually set to be different from the color of the monochromatic light emitted by the light-emitting display pixels in the central area 211.

In order to facilitate the description of the distribution of light of multiple colors emitted by the light-emitting display pixels in the surrounding area 212 in the fingerprint detection area 210 in the embodiment of the present application, the surrounding area 212 is considered to include multiple sets of sub-regions. The light-emitting display pixels in the same group of sub-regions emit light of the same color to illuminate the finger, and the light-emitting display pixels in different groups of sub-regions emit light of different colors to illuminate the finger.

It should be understood that each group of sub-regions in the multiple groups of sub-regions includes multiple sub-regions, and the number of sub-regions included in different groups of sub-regions may be the same or different. In the embodiment of the present application, the light-emitting display pixels in the surrounding area 212 emit light of multiple colors to illuminate the finger, and the light of the multiple colors is distributed at intervals in space. Correspondingly, among the sub-regions of different groups in the multiple sub-regions Arranged at intervals. For example, assuming that the multiple sets of subregions are three sets of subregions, the subregions included in the three sets of subregions are arranged at intervals.

Optionally, the areas and/or shapes of multiple subregions in the same group of subregions in the multiple sets of subregions may be the same or different; and the areas and/or shapes of subregions included in different sets of subregions may also be Same or different. Taking into account the difficulty of actual setting, multiple sub-regions in the same group of sub-regions are usually set to have the same area and shape. For ease of description, the following description takes the same area and shape of multiple sub-regions in the same group of sub-regions as an example; in addition, the areas and shapes of different groups of sub-regions in the embodiments of the present application may be the same or different.

It should be understood that the size of any subregion in the embodiments of the present application can be set according to actual applications. For example, the width of each sub-region in the surrounding area 212 can be set in the range of 0.2mm-3mm. For example, if the sub-region is a square, the side length of the square is in the range of 0.2mm-3mm; and the sub-region is assumed to be a circle. The diameter of the sub-area can be set to be 0.2mm-3mm. For another example, according to the width of the sub-region, the size of each sub-region in the surrounding region 212 may be correspondingly set to include 5-10 light-emitting display pixels, but the embodiment of the present application is not limited to this.

Optionally, the multiple sets of sub-regions included in the surrounding area 212 in the embodiment of the present application may be two sets of sub-regions or more than two sets of sub-regions. For ease of description, the multiple sets of sub-regions are used as two sets of sub-regions or Three groups of sub-regions are described in ranks.

Optionally, as a first embodiment, it is assumed that the surrounding area 212 in this embodiment of the present application includes two groups of sub-areas, which are a first group of sub-areas and a second group of sub-areas, respectively. Among them, the sub-regions in the first group of sub-regions and the sub-regions in the second group of sub-regions are arranged at intervals; the areas and shapes of the multiple sub-regions in the first group of sub-regions are the same. The area and shape of the sub-regions are the same.

Optionally, the shape of the sub-areas in the first group of sub-areas may be the same as the shape of the sub-areas in the second group of sub-areas. Specifically, the shape of the sub-areas in the first group of sub-areas and the second group of sub-areas can be set to any shape, for example, can be set to a square, a circle or a semicircle.

For example, as shown in Figs. 4 and 5, the shapes of the sub-areas in the first group of sub-areas and the second group of sub-areas may both be square. In this case, the colors of the two groups of regions can be set reasonably so that there are regions with different light intensities in the surrounding region 212. For example, you can set any group of sub-areas in the first group of sub-areas or the second group of sub-areas to be black, that is, non-light-emitting areas; while the other group is set to light-emitting areas of other colors, such as blue or yellow, so that This makes the light intensity of the first group of sub-areas and the second group of sub-areas have obvious contrast. Or, you can also set any group of sub-areas in the first group of sub-areas or the second group of sub-areas to red, and the other group to other colors, such as yellow or blue, so that both groups of sub-areas emit light, but Through the filter set above the optical sensor to intercept the red return light, the light intensity of the two groups of sub-areas can also be clearly contrasted.

For another example, as shown in FIG. 6, the shapes of the sub-areas in the first group of sub-areas and the second group of sub-areas may both be semicircular. At this time, the surrounding area 212 may also include a part of the black area, that is, the non-luminous area, that is, the black area as shown in FIG. 6. The part of the black area may make the surrounding area 212 have areas with different light intensities. The embodiment is not limited to this.

Optionally, the shape of the sub-regions in the first group of sub-regions may also be different from the shape of the sub-regions in the second group of sub-regions. Specifically, the first group of sub-regions and the second group of sub-regions can be set in any two different shapes, for example, can be set in any two shapes of a square, a circle, a semicircle, and an ellipse.

For example, as shown in FIG. 7, the shape of the sub-areas in the first group of sub-areas is a square, and the shape of the sub-areas in the second group of sub-areas is a circle. At this time, the surrounding area 212 may also include a part of the black area, that is, the non-luminous area, that is, the black area as shown in FIG. 7, and the embodiment of the present application is not limited to this.

Optionally, as a second embodiment, it is assumed that the surrounding area 212 of the embodiment of the present application includes three groups of sub-areas, which are respectively a first group of sub-areas, a second group of sub-areas, and a third group of sub-areas. Among them, the sub-regions in the first group of sub-regions, the sub-regions in the second group of sub-regions, and the sub-regions in the third group of sub-regions are arranged at intervals; multiple sub-regions in the same group of sub-regions have the same area and shape .

Optionally, the shapes of all the sub-areas in the first group of sub-areas, the second group of sub-areas and the third group of sub-areas may be set to be the same. Specifically, the shape of the sub-regions in the three groups of sub-regions may be set to any shape, for example, all may be set to be square, circular or semicircular.

For example, as shown in FIG. 8, the shapes of all the sub-areas in the first group of sub-areas, the second group of sub-areas, and the third group of sub-areas may all be square. At this time, similar to the situation where the surrounding area 212 includes the two groups of sub-areas as shown in FIGS. 4 and 5, the colors of the three groups of areas can be set reasonably so that there are areas with different light intensities in the surrounding area 212. For example, you can set any group of sub-areas from the first group of sub-areas to the third group of sub-areas to be black, that is, non-light-emitting areas; while the other two groups are set to light-emitting areas of other colors, such as blue and yellow, so that This makes the light intensities of these three groups of sub-regions have obvious contrast. Or, you can also set any group of sub-areas from the first group of sub-areas to the third group of sub-areas to be red, and the other two groups to be other colors, such as yellow and blue, so that all three groups of sub-areas emit light, but Through the filter set above the optical sensor to intercept the red return light, the light intensity of the three groups of sub-regions can also be clearly contrasted.

For another example, as shown in FIG. 9, the shapes of all the sub-regions in the first group of sub-regions, the second group of sub-regions, and the third group of sub-regions may all be semicircular. At this time, the surrounding area 212 may also include a part of the black area, that is, the non-luminous area, that is, the black area as shown in FIG. 9, and the embodiment of the present application is not limited to this.

Optionally, the shapes of the sub-areas in different groups of sub-areas may also be set to be different. Specifically, the first group of sub-regions, the second group of sub-regions, and the third group of sub-regions can be set to any two or three different shapes, that is, there may be two groups of sub-regions with the same shape in the three groups of sub-regions. , And the other group has a different shape, or the three groups of sub-regions can also be set to three completely different shapes. For example, the three groups of sub-regions can be set to any two or three shapes among square, circle, semicircle and ellipse.

For example, as shown in FIG. 10, the shape of the sub-areas in the first group of sub-areas is square, and the shapes of the sub-areas in the second group of sub-areas and the third group of sub-areas are both circular. At this time, the surrounding area 212 may also include a part of a black area, that is, a non-light emitting area, that is, a black area as shown in FIG. 10, and the embodiment of the present application is not limited to this.

In the embodiment of the present application, according to the above content, the light-emitting display pixels in the fingerprint detection area 210 are set to illuminate the finger to obtain a fingerprint image corresponding to the finger. The central part of the fingerprint image is used for fingerprint identification, and the fingerprint image The surrounding part can be used for fingerprint anti-counterfeiting authentication.

Specifically, the central area 211 of the fingerprint detection area 210 illuminates the finger with monochromatic light, and the corresponding optical sensor 320 obtains the part of the returned light and generates the central part of the fingerprint image. The central part is the image with the fingerprint of the finger. The central part of the fingerprint image performs fingerprint recognition.

In addition, the surrounding area 212 of the fingerprint detection area 210 illuminates the finger with spatially spaced light of multiple colors, and the optical sensor 320 obtains the part of the returned light and generates the surrounding part of the fingerprint image. The surrounding part can be used for fingerprint anti-counterfeiting authentication. Specifically, a deep learning algorithm may be used to determine whether the fingerprint image to be detected is a fingerprint image of a real finger according to the surrounding part in the fingerprint image to be detected.

Common fake fingerprints include milky white rubber fingerprints, transparent rubber fake fingerprints, yellow 2D fake fingerprints, black rubber fingerprints, and flesh-colored 3D rubber fingerprints. Taking into account that fake fingerprints are usually produced by an inverted mold process, this technique limits the production of fake fingerprints from the fingerprint material to the material behind the fingerprint, which is usually homogeneous and uniform. However, a real fingerprint is composed of different layers. For example, a human finger can generally include structures such as the epidermis, dermis, body tissue, and phalanges.

Therefore, the isotropic material and structure are far from the structure of the real fingerprint. When a certain interval of light hits the finger and then is imaged by the optical fingerprint device, the return light signal received by the optical fingerprint device can be divided into two parts, one is the return light directly reflected by the fingerprint surface, and the other is inside the fingerprint Light that returns after scattering. Moreover, different colors of light hit the real and fake fingerprints, and the amount of signal shown is also different. True and false fingerprints have different characteristics between the reflected light and internally scattered light due to the material and structure of the fingerprint surface, and the reflected spectrum of the fingerprint is different. By distinguishing these characteristics, the true and false fingerprints can be distinguished.

It should be understood that, in the embodiment of the present application, a deep learning algorithm may be used to analyze the surrounding part of the fingerprint image to be detected to determine whether the fingerprint image to be detected is a fingerprint image of a real finger. Among them, the deep learning algorithm may include at least one of the following: Support Vector Machine (SVM), Convolutional Neural Networks (CNN), Recurrent Neural Network (RNN), and k-means aggregation Class algorithm (k-means clustering algorithm).

Specifically, taking fingerprint anti-counterfeiting authentication on any target finger as an example, the fingerprint image to be detected of the target finger is acquired, and based on the deep learning algorithm, according to the surrounding part of the fingerprint image to be detected, it is determined whether the fingerprint image to be detected is The fingerprint image of a real finger is to determine whether the target finger is a real finger.

Optionally, a deep learning algorithm may be used to determine whether the fingerprint image to be detected is a fingerprint image of a real finger according to the distribution image of the reflected light signal and/or the distribution image of the scattered light signal in the surrounding part of the fingerprint image to be detected. Wherein, the reflected light signal is the light signal returned after the light emitted by the light-emitting display pixels in the surrounding area is reflected on the surface of the target finger. Correspondingly, the distribution image of the reflected light signal may refer to the spectrum of the returned reflected light Image, or can also refer to the intensity distribution image of the returned reflected light. The scattered light signal is the light signal returned after the light emitted by the light-emitting display pixels in the surrounding area is scattered inside the target finger. Correspondingly, the distribution image of the scattered light signal may refer to the spectral image of the returned scattered light. Or it can also refer to the intensity distribution image of the returned scattered light.

This method uses one or more kinds of information such as internal scattering, external reflection, and different spectrum of fingerprints for anti-counterfeiting authentication, and the anti-counterfeiting effect is better than that of pure optical filters. Moreover, the lighting method of the fingerprint detection area 210 in the embodiment of the present application has a much lower cost than the method of using randomly distributed color filters, and other resources are consumed the same.

Optionally, the method of determining whether the fingerprint image to be detected is a fingerprint image of a real finger based on a deep learning algorithm and according to surrounding parts in the fingerprint image to be detected may also include: based on the deep learning algorithm, according to the fingerprint image to be detected The distribution image of the first light signal and/or the distribution image of the second light signal in the surrounding part of the, determining whether the fingerprint image to be detected is a fingerprint image of a real finger. Wherein, the first light signal and the second light signal are respectively the light signals of any two colors of light emitted by the light-emitting display pixels in the surrounding area 212 after irradiating the target finger. In addition, if the light-emitting display pixels in the surrounding area 212 emit more than two kinds of light, the distribution images of more kinds of light signals may be used for comparison to determine whether the fingerprint image to be detected is a fingerprint image of a real finger.

For example, take blue and red light as examples. Specifically, the distribution image of the first light signal and the distribution image of the second light signal in the surrounding part are determined, and the first light signal is that the blue light emitted by the light-emitting display pixel in the surrounding area 212 illuminates the target finger. The light signal returned later, the second light signal is the light signal returned by the red light emitted by the light-emitting display pixel in the surrounding area 212 after irradiating the target finger. Based on the deep learning algorithm, it can be determined whether the fingerprint image to be detected is a fingerprint image of a real finger according to the distribution image of the first light signal and/or the distribution image of the second light signal.

For example, the corresponding blue light intensity distribution image can be determined based on the blue light signal returned by the blue light emitted by the light-emitting display pixels in the surrounding area 212 after irradiating the target finger; and then based on the deep learning algorithm, the acquired fingerprint image to be detected The blue light intensity distribution image in the image is analyzed to determine whether the fingerprint image to be detected is a fingerprint image of a real finger.

For another example, the corresponding red light intensity distribution image can also be determined based on the red light signal returned by the red light emitted by the light-emitting display pixels in the surrounding area 212 after irradiating the target finger; and then based on the deep learning algorithm, the acquired The red light intensity distribution image in the fingerprint image to be detected is analyzed to determine whether the fingerprint image to be detected is a fingerprint image of a real finger.

For another example, a deep learning algorithm may also be used to determine whether the fingerprint image to be detected is a fingerprint image of a real finger based on the difference between the distribution image of the first optical signal and the distribution image of the second optical signal. Specifically, based on the blue light signal returned by the blue light emitted by the light-emitting display pixels in the surrounding area 212 after irradiating the target finger, the corresponding blue light intensity distribution image is determined; based on the red light emitted by the light-emitting display pixels in the surrounding area 212 The red light signal returned after the light irradiates the target finger determines the corresponding red light intensity distribution image; obtains the difference image between the blue light intensity distribution image and the red light intensity distribution image; then analyzes the difference based on the deep learning algorithm, Then it is determined whether the fingerprint image to be detected is a fingerprint image of a real finger.

Optionally, as shown in FIG. 3, the fingerprint identification device 300 may further include: a filter 330, which is disposed above the optical sensor 320, and is used to filter out the infrared light signal in the return light signal, so as to filter out such as Influence of infrared light signals such as ambient light.

In addition, the filter can also be used to filter out part of the red light. Specifically, taking the third group of sub-areas in the plurality of groups of sub-areas included in the surrounding area 212 of the fingerprint detection area 210 as an example, the third group of sub-areas may be any group of sub-areas, and the light emission in the third group of sub-areas The display pixels are used to emit red light; the filter 330 can be used to filter the light signal returned after the red light irradiates the finger, and the filter 330 can filter the light returned after the red light irradiates the finger All or part of the signal. Correspondingly, the red light signal in the fingerprint image to be detected is the red light signal after passing through the filter 330.

It should be understood that according to the above description, based on the deep learning algorithm, one or more pieces of information about the surrounding part of the fingerprint image to be detected can be analyzed to determine whether the fingerprint image to be detected is a fingerprint image of a real finger; correspondingly, in the deep learning algorithm In the modeling phase, different information may need to be collected.

Specifically, the modeling process of the deep learning algorithm may include: acquiring several sample data, the several sample data including several real finger data and several fake finger data. Wherein, the plurality of real finger data includes the surrounding parts corresponding to the surrounding area 212 in the fingerprint image obtained when a plurality of real fingers touch the fingerprint detection area 210; the plurality of fake finger data includes a plurality of fake fingers touched in the fingerprint detection area. The area 210 corresponds to the surrounding area 212 in the acquired fingerprint image. The plurality of fake fingers may include various types of fake fingers, for example, may include: milky white rubber fingers, transparent rubber fake fingers, yellow 2D fake fingers, black rubber fingers, flesh-colored 3D rubber fingers, and so on.

Considering that when the deep learning algorithm is used, it can be based on information such as the scattered light distribution, the reflected light distribution, and the distribution of different colors of light around the acquired fingerprint image. Therefore, when acquiring the several sample data, Corresponding to the different information that needs to be collected for each sample data. For example, the distribution of scattered light, the distribution of reflected light, and the distribution of light of different colors in the fingerprint image corresponding to each sample data can be collected, and the embodiment of the present application is not limited to this.

Training is performed based on the several sample data to obtain a deep learning model of fingerprint images of real and fake fingers. If there are many kinds of fake fingers collected, the deep learning model will be more accurate. According to the deep learning model, if the surrounding part of the fingerprint image to be detected of the target finger is input, after the analysis of the deep learning model, the result of whether the fingerprint image to be detected is a fingerprint image of a real finger can be output accordingly.

Therefore, in the electronic device including the fingerprint identification device of the embodiment of the present application, a monochrome illuminating finger is set in the center area of the fingerprint detection area, and a color pattern is set to illuminate the finger in the surrounding area. This edge pattern can be a periodic grid or The edge has a certain curvature pattern, or it can be multiple color lines, so that the acquired fingerprint image can be used for fingerprint recognition and fingerprint anti-counterfeiting authentication, which solves the problem that the existing under-screen optical fingerprint recognition device cannot prevent various forms of false The problem of fingerprints improves the security level of the system, thereby enhancing the user experience. In addition, the cost of the optical fingerprint module using the color patterning method of the present application is much lower than that of the color filter fingerprint module; moreover, the optical sensor chip of the embodiment of the present application has a shorter processing cycle, lower cost, and higher yield. .

For example, based on the return light directly reflected on the fingerprint surface and the return light scattered inside the fingerprint, a deep learning algorithm can be used to distinguish the spectrum of true and false fingerprints. The deep learning algorithm will be trained in advance using the historical big data of true and false fingerprints. This historical data contains various true and false fingerprints, including true and false fingerprints in various scenarios. The original fingerprint image is output to the anti-counterfeiting algorithm to distinguish true and false fingerprints. Among them, the data of a single image can be recorded. After the calibration process of removing the screen structure, specific processing can be done on the edge area of the single image, such as subtracting the value of the red area from the value of the blue area in the collected image to obtain a new Image, so that the anti-counterfeiting model obtains more original information. In this way, more characteristic information can be obtained than traditional distributed color filters, and the recognition effect is better.

FIG. 11 shows a schematic flowchart of a method 400 for off-screen fingerprint identification and anti-counterfeiting according to an embodiment of the present application. It should be understood that the method 400 may be executed by an electronic device with a display screen. For example, the electronic device may be the aforementioned electronic device 20. For example, the electronic device 20 may include a processor or a processing unit for executing the method 400.

As shown in FIG. 11, the method 400 includes: S410, acquiring a fingerprint image of a target finger to be detected, where the fingerprint image to be detected is the fingerprint image of the target finger touching the fingerprint detection area of the display screen, and the fingerprint detection area includes mutual Non-overlapping central area and surrounding area, the central area is located in the middle of the surrounding area, the light-emitting display pixels in the central area emit monochromatic light to illuminate the target finger, and the light-emitting display pixels in the surrounding area emit light of multiple colors Illuminate the target finger; S420, perform fingerprint recognition on the target finger according to the central part of the fingerprint image to be detected corresponding to the central area; S430, perform fingerprint recognition on the surrounding part corresponding to the surrounding area in the fingerprint image to be detected The target finger performs fingerprint anti-counterfeiting authentication.

Optionally, as an embodiment, performing fingerprint anti-counterfeiting authentication on the target finger according to the surrounding part of the fingerprint image to be detected corresponding to the surrounding area includes: based on a deep learning algorithm, according to the fingerprint image in the fingerprint image to be detected The surrounding part determines whether the fingerprint image to be detected is a fingerprint image of a real finger.

Optionally, as an embodiment, the step of determining whether the fingerprint image to be detected is a fingerprint image of a real finger according to the surrounding part in the fingerprint image to be detected based on a deep learning algorithm includes: The distribution image of the reflected light signal and/or the distribution image of the scattered light signal in the surrounding part to determine whether the fingerprint image to be detected is a fingerprint image of a real finger, where the reflected light signal is emitted by the light-emitting display pixels in the surrounding area The light signal returned after the light is reflected on the surface of the target finger, and the scattered light signal is the light signal returned after the light emitted by the light-emitting display pixels in the surrounding area is scattered inside the target finger.

Optionally, as an embodiment, the step of determining whether the fingerprint image to be detected is a fingerprint image of a real finger according to the surrounding part in the fingerprint image to be detected based on a deep learning algorithm includes: The distribution image of the first light signal and/or the distribution image of the second light signal in the surrounding part is used to determine whether the fingerprint image to be detected is a fingerprint image of a real finger, where the first light signal and the second light signal are respectively The light-emitting display pixels in the surrounding area display light signals of any two colors of the multiple colors of light emitted by the target finger after irradiating the target finger.

Optionally, as an embodiment, the deep learning algorithm is used to determine whether the fingerprint image to be detected is the fingerprint of a real finger according to the distribution image of the first light signal and/or the distribution image of the second light signal in the surrounding part The image includes: determining the distribution image of the first light signal and the distribution image of the second light signal in the surrounding part, where the first light signal is that the blue light emitted by the light-emitting display pixel in the surrounding area illuminates the target finger The light signal returned later, the second light signal is the light signal returned by the red light emitted by the light-emitting display pixels in the surrounding area after irradiating the target finger; based on the deep learning algorithm, according to the distribution image and the first light signal The difference of the distribution image of the second light signal determines whether the fingerprint image to be detected is a fingerprint image of a real finger.

Optionally, as an embodiment, the determination of whether the fingerprint image to be detected is a fingerprint image of a real finger according to the surrounding part in the fingerprint image to be detected based on a deep learning algorithm includes: acquiring a plurality of sample data, the plurality of The sample data includes several real finger data and several fake finger data. The several real finger data includes the surrounding parts of the fingerprint image obtained when the real finger touches the fingerprint detection area corresponding to the surrounding area, and the several fake finger data includes A number of fake fingers touch the surrounding part of the fingerprint image obtained when the fingerprint detection area is corresponding to the surrounding area; training based on the several sample data to obtain a deep learning model of fingerprint images of real and fake fingers; according to the deep learning The model determines whether the fingerprint image to be detected is a fingerprint image of a real finger according to the surrounding part in the fingerprint image to be detected.

Optionally, as an embodiment, the deep learning algorithm includes at least one of the following: a support vector machine, a convolutional neural network, a recurrent neural network, and a k-means clustering algorithm.

It should be understood that the method 400 can be applied to various electronic devices with an under-screen optical fingerprint identification device. The fingerprint identification device can be an under-screen optical fingerprint identification device including a periodic small hole array, a macro wide-angle lens solution, and a folding type. The under-screen optical fingerprint identification device and the under-screen optical fingerprint identification device of the microlens array solution are not limited to this embodiment of the present application.

A person of ordinary skill in the art may be aware that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be implemented by electronic hardware or a combination of computer software and electronic hardware. Whether these functions are executed by hardware or software depends on the specific application and design constraint conditions of the technical solution. Professionals and technicians can use different methods for each specific application to implement the described functions, but such implementation should not be considered beyond the scope of this application.

Those skilled in the art can clearly understand that, for the convenience and conciseness of description, the specific working process of the above-described system, device, and unit can refer to the corresponding process in the foregoing method embodiment, which will not be repeated here.

In the several embodiments provided in this application, it should be understood that the disclosed system, device, and method may be implemented in other ways. For example, the device embodiments described above are only illustrative. For example, the division of the units is only a logical function division, and there may be other divisions in actual implementation, for example, multiple units or components can be combined or It can be integrated into another system, or some features can be ignored or not implemented. In addition, the displayed or discussed mutual coupling or direct coupling or communication connection may be indirect coupling or communication connection through some interfaces, devices or units, and may be in electrical, mechanical or other forms.

The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the objectives of the solutions of the embodiments.

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

If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on this understanding, the technical solution of this application essentially or the part that contributes to the existing technology or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including Several instructions are used to make a computer device (which may be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage media include: U disk, mobile hard disk, read-only memory (read-only memory, ROM), random access memory (random access memory, RAM), magnetic disk or optical disk and other media that can store program code .

The above are only specific implementations of this application, but the protection scope of this application is not limited to this. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed in this application. Should be covered within the scope of protection of this application. Therefore, the protection scope of this application should be subject to the protection scope of the claims.

Claims

A fingerprint identification device, characterized in that it is arranged under a display screen of an electronic device, the display screen includes a plurality of light-emitting display pixels, the display screen includes a fingerprint detection area, and the fingerprint detection area includes a center that does not overlap each other Area and surrounding area, the central area is located in the middle of the surrounding area, and the fingerprint identification device includes:

The optical path guiding structure is used to guide the return light signal to the optical sensor, and the return light signal is the light signal returned after the light emitted by the light-emitting display pixel in the fingerprint detection area irradiates the finger, wherein the light signal in the center area The light-emitting display pixels emit monochromatic light to illuminate the finger, and the light-emitting display pixels in the surrounding area emit light of multiple colors distributed at intervals to illuminate the finger;

The optical sensor is located below the light path guiding structure, and is used to receive light signals passing through the light path guiding structure. The light signals are used to obtain a fingerprint image of the finger, and the fingerprint image corresponds to the central area The central part of is used for fingerprint identification, and the surrounding part of the fingerprint image corresponding to the surrounding area is used for fingerprint anti-counterfeiting authentication.
The fingerprint identification device according to claim 1, wherein the light emitted by the light-emitting display pixels in the surrounding area and the monochromatic light emitted by the light-emitting display pixels in the central area have a different color.
The fingerprint identification device according to claim 1 or 2, wherein the fingerprint detection area further comprises a supplemental light area located at the periphery of the surrounding area, and the light-emitting display pixels in the supplementary light area emit monochromatic light Irradiate the finger.
The fingerprint identification device according to claim 3, wherein the color of the monochromatic light emitted by the light-emitting display pixels in the supplemental light area is the same as the color of the monochromatic light emitted by the light-emitting display pixels in the central area.
The fingerprint identification device according to any one of claims 1 to 4, wherein the area of the central area is larger than the area of the surrounding area.
The fingerprint identification device of claim 5, wherein the central area is a single connected area with an area greater than or equal to 16 mm 2 .
The fingerprint identification device according to claim 5 or 6, wherein the central area is rectangular or circular.
The fingerprint identification device according to any one of claims 1 to 7, wherein the surrounding area includes multiple groups of sub-areas, and light-emitting display pixels in the same group of sub-areas in the multiple groups of sub-areas emit the same color The light illuminates the finger, and the light-emitting display pixels in different groups of sub-areas in the multiple groups of sub-areas emit light of different colors to illuminate the finger.
8. The fingerprint identification device according to claim 8, wherein the sub-areas of different groups in the plurality of sub-areas are arranged at intervals.
The fingerprint identification device according to claim 8 or 9, wherein the areas and/or shapes of the multiple sub-regions in the same group of the multiple sub-regions are the same.
The fingerprint identification device according to any one of claims 8 to 10, wherein the width of each sub-area in the plurality of groups of sub-areas is 0.2mm-3mm.
The fingerprint identification device according to any one of claims 8 to 11, wherein the multiple groups of sub-areas are two groups of sub-areas or three groups of sub-areas.
The fingerprint identification device according to claim 12, wherein the two groups of sub-areas include a first group of sub-areas and a second group of sub-areas, and the sub-areas in the first group of sub-areas have the same area and shape , The area and shape of the sub-regions in the second group of sub-regions are the same.
The fingerprint identification device according to claim 13, wherein the shape of the sub-areas in the first group of sub-areas is the same as the shape of the sub-areas in the second group of sub-areas.
The fingerprint identification device according to claim 14, wherein the shapes of the sub-areas in the first group of sub-areas and the second group of sub-areas are square, circular or semicircular.
The fingerprint identification device according to claim 13, wherein the shape of the sub-areas in the first group of sub-areas is different from the shape of the sub-areas in the second group of sub-areas.
The fingerprint identification device according to claim 16, wherein the shape of the sub-areas in the first group of sub-areas is a square, and the shape of the sub-areas in the second group of sub-areas is a circle.
The fingerprint identification device according to any one of claims 8 to 17, wherein the fingerprint identification device further comprises:

The filter is arranged above the optical sensor and used to filter the infrared light signal in the return light signal.
The fingerprint identification device according to claim 18, wherein the multiple groups of sub-areas comprise a third group of sub-areas, and light-emitting display pixels in the third group of sub-areas are used to emit red light;

The filter is used to filter the light signal returned after the red light irradiates the finger.
The fingerprint identification device according to any one of claims 1 to 19, wherein the optical path guiding structure comprises an optical lens; or,

The optical path guiding structure includes an optical collimator having a plurality of collimating units or microhole arrays, and the optical collimator is used to transmit the return light signals to the plurality of collimating units or microhole arrays respectively. The corresponding optical sensing unit in the sensing array of the optical sensor; or,

The optical path guiding structure includes a microlens array with a plurality of microlenses and a light blocking layer with a plurality of microholes, and the microlens array is used to focus the return light signal to the respective microlenses through the plurality of microlenses. The micro-holes corresponding to the light blocking layer are transmitted to the corresponding optical sensing units in the sensing array of the optical sensor through the micro-holes.
The fingerprint identification device according to any one of claims 1 to 20, wherein the monochromatic light emitted by the light-emitting display pixels in the central area is green light or cyan light, and the light-emitting display in the surrounding area The pixels emit light of multiple colors including at least two of red light, blue light, yellow light and black light.
The fingerprint identification device according to any one of claims 1 to 21, wherein the surrounding part of the fingerprint image is used to determine whether the fingerprint image to be detected is of a real finger based on a deep learning algorithm Fingerprint image.
The fingerprint identification device of claim 22, wherein the deep learning algorithm comprises at least one of the following: a support vector machine, a convolutional neural network, a recurrent neural network, and a k-means clustering algorithm.
An electronic device, characterized by comprising: the fingerprint identification device according to any one of claims 1 to 23, a display screen and a processor,

The display screen includes a plurality of light-emitting display pixels, the light-emitting display pixels are used to display images, the display screen includes a fingerprint detection area, the fingerprint detection area includes a central area and a surrounding area that do not overlap each other, and the central area is located In the middle of the surrounding area, the light-emitting display pixels in the central area emit monochromatic light to illuminate the finger, and the light-emitting display pixels in the surrounding area emit light of multiple colors distributed at intervals to illuminate the finger;

The processor is configured to generate a fingerprint image according to the light signal received by the optical sensor in the fingerprint recognition device, and perform fingerprint recognition on the finger according to the central part of the fingerprint image corresponding to the central area, and Perform fingerprint anti-counterfeiting authentication on the finger according to the surrounding part corresponding to the surrounding area in the fingerprint image.
The electronic device according to claim 24, wherein the processor is further configured to:

Based on a deep learning algorithm, it is determined whether the fingerprint image to be detected is a fingerprint image of a real finger according to the surrounding part in the fingerprint image to be detected.
The electronic device according to claim 25, wherein the processor is further configured to:

Based on the deep learning algorithm, determine whether the fingerprint image to be detected is a fingerprint image of a real finger according to the distribution image of the reflected light signal and/or the distribution image of the scattered light signal in the surrounding part, wherein the reflected light signal is The light emitted by the light-emitting display pixels in the surrounding area is reflected on the surface of the target finger, and the scattered light signal is the light emitted by the light-emitting display pixels in the surrounding area on the target finger. The light signal returned after being scattered inside.
The electronic device according to claim 25, wherein the processor is further configured to:

Based on the deep learning algorithm, according to the distribution image of the first light signal and/or the distribution image of the second light signal in the surrounding part, it is determined whether the fingerprint image to be detected is a fingerprint image of a real finger, wherein the first The optical signal and the second optical signal are respectively the optical signals returned by any two colors of light of the multiple colors emitted by the light-emitting display pixels in the surrounding area after irradiating the target finger.
The electronic device according to claim 27, wherein the processor is further configured to:

Determine the distribution image of the first light signal and the distribution image of the second light signal in the surrounding part, where the first light signal is that the blue light emitted by the light-emitting display pixels in the surrounding area illuminates the A light signal returned after the target finger, where the second light signal is a light signal returned by the red light emitted by the light-emitting display pixels in the surrounding area after irradiating the target finger;

Based on a deep learning algorithm, it is determined whether the fingerprint image to be detected is a fingerprint image of a real finger according to the difference between the distribution image of the first optical signal and the distribution image of the second optical signal.
The electronic device according to any one of claims 25 to 28, wherein the processor is further configured to:

Acquire several sample data, the several sample data including several real finger data and several fake finger data, the several real finger data including several real finger touching the fingerprint image obtained when the fingerprint detection area and the surrounding area Corresponding surrounding parts, the plurality of fake finger data includes surrounding parts corresponding to the surrounding area in the fingerprint image obtained when the plurality of fake fingers touch the fingerprint detection area;

Training based on the several sample data to obtain a deep learning model of fingerprint images of real and fake fingers;

According to the deep learning model, it is determined whether the fingerprint image to be detected is a fingerprint image of a real finger according to the surrounding part in the fingerprint image to be detected.
The electronic device according to any one of claims 25 to 29, wherein the deep learning algorithm comprises at least one of the following: a support vector machine, a convolutional neural network, a recurrent neural network, and a k-means clustering algorithm.
An under-screen fingerprint recognition and anti-counterfeiting method, characterized in that it comprises:

Obtain the fingerprint image to be detected of the target finger, the fingerprint image to be detected is the fingerprint image of the target finger touching the fingerprint detection area of the display screen, and the fingerprint detection area includes a central area and a surrounding area that do not overlap each other, so The central area is located in the middle of the surrounding area, the light emitting display pixels in the central area emit monochromatic light to illuminate the target finger, and the light emitting display pixels in the surrounding area emit light of multiple colors to illuminate the target finger ；

Performing fingerprint recognition on the target finger according to the central part corresponding to the central area in the fingerprint image to be detected;

Perform fingerprint anti-counterfeiting authentication on the target finger according to the surrounding part corresponding to the surrounding area in the fingerprint image to be detected.
The method according to claim 31, wherein said performing fingerprint anti-counterfeiting authentication on said target finger according to the surrounding part corresponding to said surrounding area in said fingerprint image to be detected comprises:

Based on a deep learning algorithm, it is determined whether the fingerprint image to be detected is a fingerprint image of a real finger according to the surrounding part in the fingerprint image to be detected.
The method according to claim 32, wherein the determining whether the fingerprint image to be detected is a fingerprint image of a real finger according to the surrounding part in the fingerprint image to be detected based on a deep learning algorithm comprises :

Based on the deep learning algorithm, determine whether the fingerprint image to be detected is a fingerprint image of a real finger according to the distribution image of the reflected light signal and/or the distribution image of the scattered light signal in the surrounding part, wherein the reflected light signal is The light emitted by the light-emitting display pixels in the surrounding area is reflected on the surface of the target finger, and the scattered light signal is the light emitted by the light-emitting display pixels in the surrounding area on the target finger. The light signal returned after being scattered inside.
The method according to claim 32, wherein the determining whether the fingerprint image to be detected is a fingerprint image of a real finger according to the surrounding part in the fingerprint image to be detected based on a deep learning algorithm comprises :

Based on the deep learning algorithm, according to the distribution image of the first light signal and/or the distribution image of the second light signal in the surrounding part, it is determined whether the fingerprint image to be detected is a fingerprint image of a real finger, wherein the first The optical signal and the second optical signal are respectively the optical signals returned by any two colors of light of the multiple colors emitted by the light-emitting display pixels in the surrounding area after irradiating the target finger.
The method according to claim 34, characterized in that, based on the deep learning algorithm, the fingerprint to be detected is determined according to the distribution image of the first light signal and/or the distribution image of the second light signal in the surrounding part Whether the image is a fingerprint image of a real finger, including:

Determine the distribution image of the first light signal and the distribution image of the second light signal in the surrounding part, where the first light signal is that the blue light emitted by the light-emitting display pixels in the surrounding area illuminates the A light signal returned after the target finger, where the second light signal is a light signal returned by the red light emitted by the light-emitting display pixels in the surrounding area after irradiating the target finger;

Based on a deep learning algorithm, it is determined whether the fingerprint image to be detected is a fingerprint image of a real finger according to the difference between the distribution image of the first optical signal and the distribution image of the second optical signal.
The method according to any one of claims 32 to 35, wherein the deep learning algorithm is used to determine whether the fingerprint image to be detected is true according to the surrounding part in the fingerprint image to be detected Finger fingerprint image, including:

Acquire several sample data, the several sample data including several real finger data and several fake finger data, the several real finger data including several real finger touching the fingerprint image obtained when the fingerprint detection area and the surrounding area Corresponding surrounding parts, the plurality of fake finger data includes surrounding parts corresponding to the surrounding area in the fingerprint image obtained when the plurality of fake fingers touch the fingerprint detection area;

Training based on the several sample data to obtain a deep learning model of fingerprint images of real and fake fingers;

According to the deep learning model, it is determined whether the fingerprint image to be detected is a fingerprint image of a real finger according to the surrounding part in the fingerprint image to be detected.
The method according to any one of claims 32 to 36, wherein the deep learning algorithm comprises at least one of the following: a support vector machine, a convolutional neural network, a recurrent neural network, and a k-means clustering algorithm.