WO2020062848A1

WO2020062848A1 - Human face identification method, photocenter calibration method and terminal

Info

Publication number: WO2020062848A1
Application number: PCT/CN2019/084183
Authority: WO
Inventors: 朱洪波; 刘昆
Original assignee: 华为技术有限公司
Priority date: 2018-09-30
Filing date: 2019-04-25
Publication date: 2020-04-02
Also published as: CN109325460A; CN109325460B

Abstract

Disclosed are a human face identification method, a photocenter calibration method and a terminal. The method is applicable to the terminal and comprises: a dot matrix projector on the terminal emits light, and a camera on the terminal collects an image to be verified; the terminal determines N first image points on the image to be verified; N is an integer greater than or equal to 1; the terminal determines, according to the N first image points and the parameters of the camera, N first object points corresponding to the N first image points; the terminal judges whether the N first object points are arranged on the emitted light of the dot matrix projector; if the N first object points are arranged on the emitted light of the dot matrix projector, the terminal judges whether the image to be verified is consistent to the prestored human face image; if the image to be verified is consistent to the prestored human face image, the terminal determines that human face identification is successful. In this way, a hacker is prevented from inputting other human face images to a mobile phone to pass the verification (images other than the one obtained by collecting the reflected light of a light emitted by the current mobile phone on an object), thereby ensuring high security.

Description

Face recognition method, optical center calibration method and terminal

This application requires that the Chinese Patent Office be filed on September 30, 2018 with the application number 201811162463.2 and the invention name be "a method of face recognition, optical center calibration method and terminal", the entire contents of which are incorporated herein by reference.

Technical field

The present application relates to the technical field of terminals, and in particular, to a face recognition method, a light center calibration method, and a terminal.

Background technique

In the prior art, there are multiple ways to unlock the terminal, such as password unlock, fingerprint unlock, face unlock, and so on. Taking the mobile phone as an example, and the face unlocking as an example, the process of the user unlocking the mobile phone through the face is roughly as follows:

Step 1: The dot-matrix projector on the mobile phone projects infrared light onto the human face, and the human face reflects the light projected by the dot-matrix projector.

Step 2: The infrared camera on the mobile phone collects the light reflected from the face to obtain a face image.

Step 3: The mobile phone compares the face image collected by the infrared camera with the face image stored in advance. If they are the same, the mobile phone is unlocked.

In the prior art, a hacker can input other face images (face images collected by an infrared camera on a mobile phone that does not perform verification) into the mobile phone. After the mobile phone obtains the face image, it can input the face image and the pre-stored face image By comparison, there is a possibility that face recognition will pass. It can be seen that, in the prior art, the face unlocking method of the terminal has low security.

Summary of the Invention

Embodiments of the present application provide a face recognition method, a light center calibration method, and a terminal, so as to improve the security of face unlocking of the terminal.

In a first aspect, an embodiment of the present application provides a face recognition method. The method is applicable to a terminal (such as a mobile phone, an iPad, etc.). The method includes: a dot matrix projector on the terminal emits light, and the The camera collects images to be verified; the terminal determines N first image points on the image to be verified; N is an integer greater than or equal to 1; and the terminal is based on the N first image points and the camera's Parameter to determine N first object points corresponding to the N first image points; the terminal determines whether the N first object points are on the emission light of the dot matrix projector; if the N number The first object point is on the emission light of the dot matrix projector, and the terminal judges whether the image to be verified is consistent with a pre-stored face image; if the image to be verified is consistent with a pre-stored face image, the The terminal determines that the face recognition is successful.

In the embodiment of the present application, when the terminal performs face recognition, after collecting the image to be verified, it can determine whether the object point corresponding to the image point on the image to be verified is on the emission light of the dot matrix projector. When the image is verified, it is obtained by collecting the light reflected by the emitted light from the local dot matrix projector on the object. In this way, it is possible to prevent hackers from inputting other face images (not images obtained by collecting the light reflected by the emitted light on the object) into the mobile phone to pass the verification. Such a face recognition method has high security. In addition, the face recognition method provided in the embodiment of the present application is implemented based on the basic optical imaging principle. The solution is simple, the calculation amount is small, and it is helpful to receive the calculation amount and improve the efficiency.

In a possible design, before the terminal determines whether the N first object points are on the emission light of the dot matrix projector, the Jth light emitting point among the K light emitting points of the dot matrix projector emits light. Point emission light, K is an integer greater than or equal to 1, J is an integer less than or equal to K, and is greater than or equal to 1; the camera on the terminal collects the first reference picture and the second reference picture; the first reference picture Is obtained by the terminal collecting an object at a first distance from the terminal, and the second reference image is obtained by collecting the object at a second distance; the second distance is greater than the first distance; The terminal selects M second image points on the first reference image, where M is an integer greater than or equal to 2; and the terminal determines an AND on the second reference image according to the M second image points and a matching algorithm. M third image points in which each second image point matches one by one, wherein the P second image point matches the P third image point, and P is An integer greater than or equal to 1 and less than or equal to M; the terminal according to the M second image points and the camera The parameters of the head determine the corresponding M second object points, and the corresponding M third object points are determined according to the M third image points and the parameters of the camera, wherein the P second object point and The Pth third object point matches; the terminal calculates coordinates of a virtual light center of the Jth light emitting point of the dot matrix transmitter, where the virtual light center is obtained by the intersection of M first straight lines, so The P-th second object point is connected to the P-th third object point to obtain the first straight line.

In the embodiment of the present application, the terminal may calibrate the virtual light center of the light emitting point on the dot matrix projector. In this process, the emission light of the virtual light center (that is, the M first straight lines), that is, the emission light of the light emitting point may be determined . In this way, the terminal can determine the emission light of the light emitting point on the dot matrix projector, so that after the terminal obtains the image to be verified, it determines whether the object point corresponding to the image point on the image to be verified is the light emitting point on the dot matrix projector. Emit light. In this way, it is possible to prevent hackers from entering other face images into the mobile phone and passing the verification as much as possible. Such a face recognition method has high security.

In a possible design, before the terminal judges whether the N first object points are on the emission light of the dot matrix projector, the Jth light emitting point among the K emitting points of the dot matrix projector Emitting light, K is an integer greater than or equal to 1, J is an integer less than or equal to K, and is greater than or equal to 1; the camera on the terminal collects a first reference picture and a second reference picture; the first reference picture is Obtained by the terminal collecting an object at a first distance from the terminal, and the second reference image is obtained by collecting the object at a second distance; the second distance is greater than the first distance; The terminal selects M second image points on the first reference picture, where M is an integer greater than or equal to 2; and the terminal determines whether the second reference picture is different from the second reference picture according to the M second image points and the matching algorithm. M third image points in which each second image point matches one by one, wherein the P second image point matches the P third image point, and P is greater than Or equal to 1, and an integer less than or equal to M; the terminal according to the M second image points and the camera Corresponding M second object points are determined according to the parameters of the M, and the corresponding M third object points are determined according to the M third image points and the parameters of the camera, wherein the P second object point is related to all The P-th third object point matching is described; the terminal calculates the coordinates of the virtual light center of the J-th light emitting point of the dot matrix transmitter, the virtual light center is obtained by the intersection of M first straight lines, The P-th second object point after drift compensation is connected to the P-th third object point after temperature drift compensation to obtain the first straight line.

In the embodiment of the present application, the terminal may perform temperature drift compensation on the coordinates of the determined object points. After the temperature drift compensation, the coordinates of the object points are more accurate, thereby obtaining more accurate virtual optical center coordinates, and improving optical center calibration. Accuracy. Further, when the coordinates of the light center and the object point are more accurate, that is, the emitted light from the light emitting point on the dot matrix projector is more accurate, and the accuracy of the emitted light from the object point corresponding to the image point on the image to be verified is higher , That is, face recognition is more accurate.

In a possible design, the terminal determining whether the N first object points are on the emission light of the dot matrix projector includes: the terminal according to the K virtual lights of the dot matrix transmitter The coordinates of the center and the equation of K * M emission rays determine whether the N first object points are on the emission rays of K emission points.

In the embodiment of the present application, during the calibration process, the terminal obtains the equations of the M emission rays corresponding to each of the K illumination points, and obtains the equations of K * M emission rays in total. After the terminal obtains the image to be verified, it determines whether an object point corresponding to an image point on the image to be verified is an equation of the K * M emitted rays. In this way, it is possible to prevent hackers from entering other face images into the mobile phone and passing the verification as much as possible. Such a face recognition method has high security.

In a possible design, the terminal determining whether the N first object points are on the emission light of the dot matrix projector includes: the terminal according to the K virtual lights of the dot matrix transmitter The coordinates of the center and the coordinates of the calibrated object points are used to determine whether the N first object points are on at least one of the K lines of the virtual optical center and the calibrated object points. On at least one of the K lines, it is determined that the N first object points are on the emission light of the dot matrix projector, and if it is not on at least one of the K lines, it is determined The N first object points are not on the emission light of the dot matrix projector.

In the embodiment of the present application, during the calibration process, the terminal obtains the light center and the calibrated object point of each of the K light emitting points. After the terminal obtains the image to be verified, it is determined whether an object point corresponding to an image point on the image to be verified is on at least one of the light center of a light emitting point and a line connecting the calibrated object point. In this way, it is possible to prevent hackers from entering other face images into the mobile phone and passing the verification as much as possible. Such a face recognition method has high security.

In a possible design, the dot-matrix projector on the terminal emits light, the terminal is in a lock screen state before the camera on the terminal collects the image to be verified, and after the terminal determines that the face recognition is successful The method further includes: unlocking the terminal.

The face recognition method provided in the embodiment of the present application can unlock the device, which helps improve the security of face unlocking.

In a possible design, the dot matrix projector on the terminal emits light, and before the camera on the terminal collects the image to be verified, the terminal displays a payment verification interface; after the terminal determines that the face recognition is successful The method further includes: the terminal executing a payment process.

The face recognition method provided in the embodiment of the present application can also perform online payment, which helps improve payment security.

In a possible design, the dot-matrix projector on the terminal emits light, and before the camera on the terminal collects the image to be verified, the terminal displays a permission or password setting interface; the terminal determines face recognition After success, the method further includes: the terminal performing a permission or password setting operation.

The face recognition method provided in the embodiment of the present application can also set permissions or passwords, which helps improve the security of the password or permission settings.

In a possible design, if the image to be verified is consistent with a pre-stored face image, the terminal determines that face recognition has failed.

In a second aspect, an embodiment of the present application provides a method for calibrating an optical center. The method is applicable to a terminal having a dot matrix projector or other terminals capable of projecting light. The method includes: the Jth light emitting point among the K light emitting points of the dot matrix projector on the terminal emits light, K is an integer greater than or equal to 1, J is an integer less than or equal to K, and greater than or equal to 1;

The camera on the terminal collects a first reference picture and a second reference picture; the first reference picture is obtained by the terminal collecting objects at a first distance from the terminal, and the second reference picture is the Obtained by collecting the object at a second distance; the second distance is greater than the first distance;

The terminal selects M second image points on the first reference picture, where M is an integer greater than or equal to 2;

Determining, by the terminal according to the M second image points and the matching algorithm, M third image points on the second reference picture that are one-to-one matched with each of the M second image points, Wherein, the P-th second image point matches the P-th third image point, and P is an integer greater than or equal to 1 and less than or equal to M;

The terminal determines corresponding M second object points according to the M second image points and parameters of the camera, and determines corresponding M third objects according to the M third image points and parameters of the camera. An object point, wherein the P-th second object point matches the P-th third object point;

The terminal calculates coordinates of a virtual light center of the Jth light emitting point of the dot matrix transmitter, the virtual light center is obtained by intersecting M first straight lines, and the Pth second object point and the The P-th third object point is connected to obtain the first straight line.

In a third aspect, an embodiment of the present application further provides a method for calibrating an optical center, which is applicable to a terminal having a dot matrix projector or other terminals capable of projecting light. The method includes: the Jth light emitting point among the K light emitting points of the dot matrix projector on the terminal emits light, K is an integer greater than or equal to 1, J is an integer less than or equal to K, and is greater than or equal to 1; Camera captures a first reference picture and a second reference picture; the first reference picture is obtained by the terminal collecting objects at a first distance from the terminal, and the second reference picture is that the acquisition is in the second The second distance is greater than the first distance; the terminal selects M second image points on the first reference picture, where M is an integer greater than or equal to 2; the terminal According to the M second image points and the matching algorithm, M third image points on the second reference picture that are matched one by one with each second image point of the M second image points, respectively, The P second image points match the Pth third image point, where P is an integer greater than or equal to 1 and less than or equal to M; the terminal is based on the M second image points and the camera's The corresponding M second object points are determined by parameters, and are determined according to the M third image points and the parameters of the camera. Corresponding M third object points, wherein the Pth second object point matches the Pth third object point; the terminal calculates a virtual number of the Jth light emitting point of the dot matrix transmitter The coordinates of the optical center. The virtual optical center is obtained by the intersection of M first straight lines. The P-th second object point after temperature drift compensation is connected to the P-th third object point after temperature drift compensation. The first straight line is obtained.

In a fourth aspect, an embodiment of the present application further provides a face recognition method, which is applicable to a terminal (such as a mobile phone, an iPad, etc.). The method includes: a dot matrix projector on the terminal emits light, and the terminal on the terminal Camera detects the image to be verified; the terminal determines whether the image to be verified is consistent with a pre-stored face image; if the image to be verified is consistent with a pre-stored face image, the terminal determines that the N first image points of N; N is an integer greater than or equal to 1; the terminal determines the N first image points corresponding to the N first image points according to the N first image points and parameters of the camera The object point; the terminal judges whether the N first object points are on the emission light of the dot matrix projector; if the N first object points are on the emission light of the dot matrix projector, determining Face recognition succeeded.

In a fifth aspect, an embodiment of the present application provides a terminal, including a dot matrix projector, a camera, a processor, and a memory. Wherein, the dot matrix projector is used to emit light; the camera is used to collect images to be verified; the memory is used to store one or more computer programs; when the one or more computer programs stored in the memory are executed by a processor When enabling the terminal to implement the first aspect or any possible design method of the first aspect; or when the one or more computer programs stored in the memory are executed by the processor, enable the terminal to implement the fourth aspect or the first aspect Any of the four possible design methods.

According to a sixth aspect, an embodiment of the present application provides a terminal, including a dot matrix projector, a camera, a processor, and a memory. Wherein, the Jth light emitting point among the K light emitting points of the dot matrix projector emits light; the camera is used to collect the first reference picture and the second reference picture; the memory is used to store one or more computer programs; When the one or more computer programs stored in the memory are executed by the processor, the terminal can implement the second aspect or any one of the possible design methods of the second aspect; or when the one or more computer programs stored in the memory are implemented by the processor When the processor executes, the terminal can implement the third aspect or any one of the possible design methods of the third aspect.

According to a seventh aspect, an embodiment of the present application further provides a terminal, where the terminal includes a module / unit that executes the first aspect or a method of any possible design of the first aspect; or the terminal includes performing the second aspect Aspect or the module / unit of any possible design method of the second aspect; or, the terminal includes a module / unit that executes the third aspect or any possible design method of the third aspect; or The terminal includes a module / unit that executes the fourth aspect or the method of any possible design of the fourth aspect;

These modules / units can be implemented by hardware, and can also be implemented by hardware executing corresponding software.

According to an eighth aspect, a computer-readable storage medium is further provided in an embodiment of the present application. The computer-readable storage medium includes a computer program, and when the computer program is run on a terminal, the terminal executes the first aspect or the foregoing first aspect. Any one of the possible design methods in one aspect; or, when the computer program runs on the terminal, causing the terminal to execute the second aspect or any one of the foregoing possible design methods in the second aspect; or, when the computer When the program is run on the terminal, the terminal is caused to execute the third aspect or any one of the foregoing third aspect possible design methods; or when the computer program is run on the terminal, the terminal is caused to execute the fourth aspect or Any one of the possible design methods of the fourth aspect.

In a ninth aspect, an embodiment of the present application further provides a computer program product that, when the computer program product runs on a terminal, causes the terminal to execute the first aspect or any one of the foregoing possible designs of the first aspect. A method; or when the computer program product is run on a terminal, causing the terminal to execute the second aspect or any one of the foregoing possible design methods of the second aspect; or when the computer program product is on a terminal When running, causing the terminal to execute the third aspect or any one of the foregoing possible design methods of the third aspect; or when the computer program product is running on the terminal, causing the terminal to execute the fourth aspect or the foregoing Any possible design method of the fourth aspect.

BRIEF DESCRIPTION OF THE DRAWINGS

1 is a schematic diagram of an image plane coordinate system, a camera coordinate system, and a world coordinate system according to an embodiment of the present application;

2 is a schematic structural diagram of a mobile phone according to an embodiment of the present application;

3 is a schematic diagram of an application scenario according to an embodiment of the present application;

4 is a schematic structural diagram of a mobile phone according to an embodiment of the present application;

5 is a schematic flowchart of calibrating a virtual optical center of a dot matrix projector provided by an embodiment of the present application;

6 is a schematic diagram of a virtual optical center calibration process of a dot matrix projector provided by an embodiment of the present application;

7 is a schematic diagram of a first reference diagram and a second reference diagram provided by an embodiment of the present application;

8 is a schematic diagram of light emitted from a light emitting point on a dot matrix projector provided by an embodiment of the present application;

9 is a schematic structural diagram of a dot matrix projector provided by an embodiment of the present application;

10 is a schematic flowchart of a face recognition method according to an embodiment of the present application;

11 is a schematic flowchart of another face recognition method according to an embodiment of the present application;

12 is a schematic diagram of a mobile phone display interface according to an embodiment of the present application;

13 is a schematic diagram of a mobile phone display interface according to an embodiment of the present application;

FIG. 14 is a schematic structural diagram of a terminal according to an embodiment of the present application.

detailed description

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

In the following, some terms in this application are explained so as to facilitate understanding by those skilled in the art.

The image plane coordinate system involved in the embodiment of the present application is a coordinate system established on the imaging plane of the camera. Generally, the origin of the image plane coordinate system is the center of the imaging plane. The camera collects the light reflected by the object and presents these light on the imaging plane to obtain an image of the object. In the following, the image plane coordinate system is represented by o1-u-v. Please refer to FIG. 1. In FIG. 1, o1 is the center of the imaging plane, and the image plane coordinate system is the origin, and the u axis and the v axis are the coordinate axes of the image plane coordinate system, respectively. For example, the u axis is the horizontal axis of the image plane coordinate system, and the v axis is the vertical axis of the image plane coordinate system.

The camera coordinate system involved in the embodiment of the present application, that is, the coordinate system whose origin is the center of the camera, and hereinafter, the camera coordinate system is represented by o2-x-y-z. Please continue to refer to FIG. 1. In FIG. 1, o2 is the camera center and the origin of the camera coordinate system. The x-axis, y-axis, and z-axis are the coordinate axes of the camera coordinate system.

The world coordinate system, that is, the absolute coordinate system involved in the embodiments of the present application, can be used to calibrate the position of a camera or a dot matrix projector. In the following, the world coordinate system is represented by o3-X-Y-Z. Please continue to refer to FIG. 1. In FIG. 1, o3 is the origin of the world coordinate system, and the X axis, Y axis, and Z axis are the coordinate axes of the world coordinate system.

Generally, the points in the image plane coordinate system can be converted into the camera coordinate system or the world coordinate system through corresponding conversion formula conversion (described later). Of course, the points in the camera coordinate system or the world coordinate system can be converted into the image plane coordinate system through corresponding conversion formula conversion (described later).

The image points involved in the embodiments of the present application are points on an image obtained by a camera, that is, points in an image plane coordinate system.

The object points involved in the embodiments of the present application, the points on the object to be photographed, usually, there is a conversion relationship between the object points and the image points. For example, the camera can determine an object point corresponding to the image point according to an image point on the captured image and a conversion formula containing the optical parameters of the camera.

Please continue to refer to FIG. 1, the corresponding image point of the object point W on the imaging plane is W ′. The object point W can be represented in a camera coordinate system, and the image point W 'can be represented in an image plane coordinate system.

The images involved in this embodiment of the present application, such as the first reference image, the second reference image, the image to be verified, or a pre-stored face image, can be in the form of a picture or a collection of data, such as some parameters (such as pixels, Color information, etc.).

The multiple involved in the embodiments of the present application refers to two or more.

In addition, it should be understood that in the description of this application, the words "first" and "second" are used only for the purpose of distinguishing descriptions, and cannot be understood as indicating or implying relative importance, nor as indicating Or imply order.

A terminal, a graphical user interface (GUI) for such a terminal, and embodiments for using such a terminal are described below. In some embodiments of the present application, the terminal may be a portable terminal including a dot matrix projector and an infrared camera, such as a mobile phone, a tablet computer, a wearable device (such as a smart watch) with a wireless communication function, and the like. Exemplary embodiments of portable terminals include, but are not limited to,

Or a portable terminal with another operating system. The above portable terminal may also be another portable terminal, as long as it can realize the function of projecting light and image acquisition (function of acquiring light projected by the local machine to obtain an image). It should also be understood that, in some other embodiments of the present application, the above-mentioned terminal may not be a portable terminal, but a desktop computer capable of implementing light projection and image acquisition functions (functions of acquiring light projected by the local machine to obtain images).

Generally, the terminal supports multiple applications. For example, one or more of the following applications: a camera application, an instant messaging application, and the like. Among them, there can be multiple instant messaging applications. Such as WeChat, Tencent chat software (QQ), WhatsApp Messenger, Line Me (Line), Kakao talk, Ding Ding and so on. Through instant messaging applications, users can send text, voice, pictures, video files, and other files to other contacts; or users can use instant messaging applications to implement voice and video calls with other contacts.

Taking the terminal as a mobile phone as an example, FIG. 2 shows a schematic structural diagram of the mobile phone 100.

The mobile phone 100 may include a processor 110, an external memory interface 120, an internal memory 121, a universal serial bus (USB) interface 130, a charge management module 140, a power management module 141, a battery 142, an antenna 1, an antenna 2, Mobile communication module 151, wireless communication module 152, dot matrix projector 160, audio module 170, speaker 170A, receiver 170B, microphone 170C, headphone interface 170D, sensor module 180, button 190, motor 191, indicator 192, camera 193, A display screen 194, and a subscriber identification module (SIM) card interface 195. The sensor module 180 may include a pressure sensor 180A, a gyro sensor 180B, an air pressure sensor 180C, a magnetic sensor 180D, an acceleration sensor 180E, a distance sensor 180F, a proximity light sensor 180G, a fingerprint sensor 180H, a temperature sensor 180J, a touch sensor 180K, and ambient light. Sensor 180L, bone conduction sensor 180M, etc.

It can be understood that the structure illustrated in the embodiment of the present invention does not constitute a specific limitation on the mobile phone 100. In other embodiments of the present application, the mobile phone 100 may include more or fewer parts than shown, or some parts may be combined, or some parts may be split, or different parts may be arranged. The illustrated components can be implemented in hardware, software, or a combination of software and hardware.

The processor 110 may include one or more processing units. For example, the processor 110 may include an application processor (AP), a modem processor, a graphics processing unit (GPU), and an image signal. Processor (image signal processor, ISP), controller, memory, video codec, digital signal processor (DSP), baseband processor, and / or neural-network processing unit, NPU) and so on. Among them, different processing units may be independent devices or integrated in one or more processors.

The controller may be a nerve center and a command center of the mobile phone 100. The controller can generate operation control signals according to the instruction operation code and timing signals, and complete the control of fetching and executing instructions.

The processor 110 may further include a memory for storing instructions and data. In some embodiments, the memory in the processor 110 is a cache memory. The memory may store instructions or data that the processor 110 has just used or used cyclically. If the processor 110 needs to use the instruction or data again, it can be directly called from the memory. Repeated accesses are avoided and the waiting time of the processor 110 is reduced, thereby improving the efficiency of the system.

The mobile phone 100 implements a display function through a GPU, a display screen 194, and an application processor. The GPU is a microprocessor for image processing and is connected to the display 194 and an application processor. The GPU is used to perform mathematical and geometric calculations for graphics rendering. The processor 110 may include one or more GPUs that execute program instructions to generate or change display information.

The display screen 194 is used to display images, videos, and the like. The display screen 194 includes a display panel. The display panel can use a liquid crystal display (LCD), an organic light-emitting diode (OLED), an active matrix organic light emitting diode or an active matrix organic light emitting diode (active-matrix organic light-emitting diode). emitting diodes (AMOLED), flexible light-emitting diodes (FLEDs), Miniled, MicroLed, Micro-oLed, quantum dot light emitting diodes (QLEDs), etc. In some embodiments, the mobile phone 100 may include one or N display screens 194, where N is a positive integer greater than 1.

The camera 193 is used to capture still images or videos. Generally, the camera 193 may include a photosensitive element such as a lens group and an image sensor, where the lens group includes a plurality of lenses (convex lenses or concave lenses) for collecting the light signals reflected by the object to be captured and transmitting the collected light signals to the image sensor. . The image sensor generates an image of an object to be captured according to the light signal. If the mobile phone 100 is currently in a lock screen state, the image sensor sends the generated image to the processor 110, and the processor 110 runs the face recognition algorithm provided in the embodiment of the present application to identify the image. If the mobile phone 100 currently displays a viewfinder interface of a camera application, the display screen 194 displays the image in the viewfinder interface.

The dot matrix projector 160 is used to project light. The light projected by the dot matrix projector 160 may be visible light, or infrared light (for example, infrared laser light). Taking infrared light as an example, the camera 193 may be an infrared camera to collect infrared laser light emitted by a dot matrix projector. The camera 193 shown in FIG. 1 includes 1-N cameras. If a camera is included, the visible light camera used for taking pictures and videos used by the camera application and the camera used for face recognition are the same camera. If multiple cameras are included, the cameras used by the camera application and the cameras used for face recognition may be different cameras. For example, the camera used by the camera application is a visible light camera, and the camera used for face recognition is an infrared camera.

The internal memory 121 may be used to store computer executable program code, where the executable program code includes instructions. The processor 110 executes various functional applications and data processing of the mobile phone 100 by executing instructions stored in the internal memory 121. The internal memory 121 may include a storage program area and a storage data area. The storage program area may store an operating system, at least one application required by a function (such as a sound playback function, an image playback function, etc.) and the like. The storage data area can store data (such as audio data, phone book, etc.) created during the use of the mobile phone 100. In addition, the internal memory 121 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, a universal flash memory (UFS), and the like.

Among them, the distance sensor 180F is used to measure distance. The mobile phone 100 can measure the distance by infrared or laser. In some embodiments, when shooting a scene, the mobile phone 100 may use a distance sensor 180F to measure the distance to achieve fast focusing. In other embodiments, the mobile phone 100 may also use the distance sensor 180F to detect whether a person or an object is approaching.

Among them, the proximity light sensor 180G may include, for example, a light emitting diode (LED) and a light detector, such as a photodiode. The light emitting diode may be an infrared light emitting diode. The mobile phone 100 emits infrared light through a light emitting diode. The mobile phone 100 uses a photodiode to detect infrared reflected light from nearby objects. When sufficient reflected light is detected, it can be determined that there is an object near the mobile phone 100. When insufficient reflected light is detected, the mobile phone 100 may determine that there is no object near the mobile phone 100. The mobile phone 100 can use the proximity light sensor 180G to detect that the user is holding the mobile phone 100 close to the ear to talk, so as to automatically turn off the screen to save power. The proximity light sensor 180G can also be used in holster mode, and the pocket mode automatically unlocks and locks the screen.

The ambient light sensor 180L is used to sense ambient light brightness. The mobile phone 100 can adaptively adjust the brightness of the display screen 194 according to the perceived ambient light brightness. Ambient light sensor 180L can also be used to automatically adjust white balance when taking pictures. The ambient light sensor 180L can also cooperate with the proximity light sensor 180G to detect whether the mobile phone 100 is in a pocket to prevent accidental touch.

The fingerprint sensor 180H is used to collect fingerprints. The mobile phone 100 can use the collected fingerprint characteristics to realize fingerprint unlocking, access application lock, fingerprint photographing, fingerprint answering calls, etc.

The temperature sensor 180J is used to detect the temperature. In some embodiments, the mobile phone 100 executes a temperature processing strategy using the temperature detected by the temperature sensor 180J.

The touch sensor 180K is also called "touch panel". The touch sensor 180K may be disposed on the display screen 194, and the touch screen is composed of the touch sensor 180K and the display screen 194, which is also referred to as a "touch screen". The touch sensor 180K is used to detect a touch operation acting on or near it. The touch sensor can pass the detected touch operation to the application processor to determine the type of touch event. A visual output related to the touch operation may be provided through the display screen 194. In other embodiments, the touch sensor 180K may also be disposed on the surface of the mobile phone 100, which is different from the position where the display screen 194 is located.

In addition, the mobile phone 100 can implement audio functions through an audio module 170, a speaker 170A, a receiver 170B, a microphone 170C, a headphone interface 170D, and an application processor. Such as music playback, recording, etc. The mobile phone 100 can receive the input of the key 190 and generate a key signal input related to the user settings and function control of the mobile phone 100. The mobile phone 100 may use the motor 191 to generate a vibration prompt (such as an incoming call vibration prompt). The indicator 192 in the mobile phone 100 can be an indicator light, which can be used to indicate the charging status, power change, and can also be used to indicate messages, missed calls, notifications, and so on. The SIM card interface 195 in the mobile phone 100 is used to connect a SIM card. The SIM card can be inserted and removed from the SIM card interface 195 to achieve contact and separation with the mobile phone 100.

Please refer to FIG. 3, which is a schematic diagram of an application scenario provided by an embodiment of the present application. The mobile phone in FIG. 3 uses the mobile phone 100 shown in FIG. 2 as an example. As shown in FIG. 3, when the user points the mobile phone 100 toward the user, when the distance sensor 180F (not shown in FIG. 3) on the mobile phone 100 detects that an object (ie, a person) is approaching, the dot matrix projector 160 emits light. The object reflects the emitted light of the dot matrix projector 160, and the reflected light is collected by the camera 193 to obtain an image to be verified (that is, a face image).

The processor 110 in the mobile phone 100 runs the code of the face recognition algorithm provided in the embodiment of the present application (the code of the face recognition algorithm may be stored in the internal memory 121 or stored in the storage space of the camera 193 itself), and judges whether the Verify whether the image is obtained by collecting the light reflected by the emitted light from the dot matrix projector 160 on the object; if it is, then the image to be verified is further matched with the face image stored in advance; if not, a prompt message is output to The user is reminded that the image to be verified is not obtained by collecting the light reflected by the emitted light from the local dot matrix projector 160 on the object, which poses a security risk.

It can be seen that the face recognition method provided in the embodiment of the present application has a new step compared with the aforementioned face recognition method in the prior art. This step is to determine whether an image to be verified (for example, a face image) is It is obtained by collecting the light reflected by the emitted light from the local dot matrix projector on the object. In practical applications, the newly added step may be performed before comparing the image to be verified with a face image stored in advance, or may be performed after comparing the image to be verified with a face image stored in advance. For example, the processor 110 in the mobile phone 100 executes the code of the face recognition algorithm provided in the embodiment of the present application, and compares whether the image to be verified (such as a face image) is consistent with the face image stored in advance; if it is, further judges whether It is verified whether the image is obtained by collecting the light reflected by the emitted light from the dot matrix projector 160 on the object.

From the above description, it can be known that when the mobile phone 100 provided in the embodiment of the present application performs face recognition, it can be determined whether the image to be verified (that is, the face image) is collected and reflected by the light emitted by the local dot matrix projector 160 on the object. Get the light. In this way, it is possible to prevent hackers from inputting other face images (not images obtained by collecting the light reflected by the emitted light on the object) into the mobile phone to pass the verification. Such a face recognition method has high security.

In order to facilitate the description of the face recognition algorithm provided in the embodiment of the present application, the face recognition algorithm of the embodiment of the present application will be described below through components related to the face recognition algorithm provided in the embodiment of the present application. For the components in FIG. 1, refer to the related description about FIG. 1. It should be noted that in FIG. 4, the processor 110 is integrated with the application processor 110-1 as an example.

As shown in FIG. 4, the distance sensor 180F in the mobile phone 100 can detect whether an object approaches. When the distance sensor 180F detects that an object (such as a human face) is approaching, it sends an instruction to the application processor 101-1, which is used to indicate that an object is approaching. After receiving the instruction, the application processor 110-1 activates the dot matrix projector 160 to project light. The application processor 110-1 triggers the activation of the camera 193 to collect the light reflected by the object to obtain an image to be verified (such as a face image).

In practical applications, when the proximity sensor 180F detects an object approaching, it can also generate a command to trigger the dot matrix projector 160 and the camera 193, and send the command to the application processor 110-1 to notify the application processor 110. -1 activates the dot matrix projector 160 and the camera 193. Of course, the dot matrix projector 160 and the camera 193 in the mobile phone 100 may also be turned on periodically or always on. For example, the dot matrix projector 160 may periodically project light, and the camera 193 periodically collects images to be verified.

After the camera 193 captures the image to be verified, it sends the image to be verified to the application processor 110-1. The application processor 110-1 runs the code of the face recognition algorithm stored in the internal memory 121 (not shown in FIG. 4) to recognize the image to be verified. If the identification is passed, the display screen 194 is unlocked. For example, the main interface of the mobile phone 100 may be displayed by switching from the lock screen.

The application processor 110-1 runs the code of the face recognition algorithm provided in the embodiment of the present application, and the identification of the image to be verified may include two processes. The first process. The application processor 110-1 determines whether the image to be verified is obtained by collecting light reflected from the object by the light emitted from the local dot matrix projector 160. In the second process, the application processor 110-1 determines whether the image to be verified is consistent with the face image stored in advance.

Please continue to refer to FIG. 3, the camera 193 collects reflected light, and the reflected light is reflected by an object (for example, a human face) on the emitted light of the dot matrix projector 160. Therefore, in the first process described above, the mobile phone 100 can determine whether the object point on the object is on the light emitted by the dot matrix projector 160. Therefore, the mobile phone 100 may first determine the position of the emitted light of the dot matrix projector 160 in space.

The following describes the process by which the mobile phone 100 determines the position of the emitted light of the dot matrix projector 160 in space.

In the embodiment of the present application, the process in which the mobile phone 100 determines the position of the emitted light of the dot matrix projector 160 in space can be implemented by virtual optical center calibration. Before the mobile phone 100 leaves the factory, the virtual optical center of the dot matrix projector can be calibrated, that is, the process in which the mobile phone 100 determines the position coordinates of the virtual optical center of the dot matrix projector. Please refer to FIG. 5, which is a schematic diagram of a virtual optical center calibration process of a dot matrix projector provided by an embodiment of the present application. As shown in FIG. 5, the process includes:

Step 1: The mobile phone 100 obtains a first reference picture and a second reference picture, and the first reference picture and the second reference picture include the same photographic subject.

Please refer to FIG. 6, before the mobile phone 100 leaves the factory, the designer may set a calibration plate at a Znear at a first distance (for example, 20 cm) from the dot matrix projector 160. The dot matrix projector 160 on the mobile phone 100 projects light onto the calibration plate. The light reflected by the calibration plate is collected by the camera 193 to obtain a first reference image. The designer moves the position of the calibration plate, and moves the calibration plate to Zfar at a second distance (for example, 70 cm) from the dot matrix projector 160. The light reflected by the calibration plate located at Zfar is collected again by the camera 193 to obtain a second reference picture. It can be seen that the first reference picture and the second reference picture are images obtained by photographing the same subject at different positions.

It should be noted that in FIG. 6, the first reference picture and the second reference picture are both presented on the imaging plane. In FIG. 6, the first reference picture and the second reference picture are not distinguished on the imaging plane, but actually The first reference picture and the second reference picture are two different pictures formed on the imaging plane.

It should be noted that the calibration plate may be a white board, and the light projected by the dot matrix projector 160 is visible light or infrared light. Taking infrared light as an example, in practical applications, the dot matrix projector 160 can project infrared light in the form of structured light (that is, the infrared light is projected in a specific shape, that is, the light projected onto the surface of the object has a specific shape. The specific shape may be a straight line, speckles, etc.); or the calibration plate may be a plate that has undergone special treatment. For example, the calibration plate is provided with special marks for identifying different positions, and the mobile phone 100 obtains the first reference picture and the second reference. In the drawing, the special mark on the first reference picture and the special mark on the second reference picture can be determined.

Please refer to FIG. 7, which are schematic diagrams of a first reference diagram and a second reference diagram provided by an embodiment of the present application. The first reference picture and the second reference picture are images obtained by the camera 193 on the calibration plates located at different positions. Therefore, the display position of each object (such as a special mark) on the first reference picture and the second reference picture is different. As shown in FIG. 7, the dark areas on the first reference picture and the second reference picture are special marks.

Step 2: The mobile phone 100 determines position coordinates of two image points Q1 and P1 on the first reference picture.

Please continue to refer to FIG. 7. The first reference picture and the second reference picture are for the same photographic object (calibration plate or speckle projected by the dot-matrix projector) at different positions. The photographic object may be the calibration plate. Projected speckles). The mobile phone 100 may take any two image points on the first reference picture, that is, Q1 and P1. Alternatively, if the dot projector projects speckles, the two image points Q1 and P1 may be respective center points of some two speckles on the first reference picture.

Please refer to FIG. 6, since the first reference picture and the second reference picture are presented on the imaging plane, the image points Q1 and P1 on the first reference picture determined by the mobile phone 100 are coordinates in the image plane coordinate system ouv .

Step 3: The mobile phone 100 determines Q2 and P2 on the second reference diagram according to Q1 and P1 on the first reference diagram, where Q2 corresponds to Q1 and P2 corresponds to P1.

Since the first reference picture and the second reference picture are obtained by photographing the calibration boards at different positions, the same object (such as a special mark: dark area) on the calibration board has different display positions on the two reference pictures. The mobile phone 100 may determine a point corresponding to the one image point on the second reference image according to one image point on the first reference image. The mobile phone 100 may determine Q2 and P2 on the second reference diagram according to a prior art matching algorithm (such as a similarity matching algorithm). Regarding the matching algorithm, this application will not go into details.

Please continue to refer to FIG. 7. After the mobile phone 100 determines Q1 and P1 on the first reference picture, it can determine Q2 corresponding to Q1 and P2 corresponding to P1 on the second reference picture.

It should be noted that, please refer to FIG. 6, although in FIG. 6, the first reference picture and the second reference picture are not distinguished on the imaging plane. However, the image points on the first reference picture and the second reference picture are in the image plane coordinate system. Therefore, after the mobile phone 100 determines Q2 and P2 on the second reference diagram according to Q1 and P1 on the first reference diagram, Q1, P1, Q2, and P2 can be marked in the image plane coordinate system at the same time.

The fourth step: the mobile phone 100 determines the object point Q3 according to the image point Q1 on the first reference picture, and determines the object point P3 based on the image point P1; the mobile phone 100 determines the object point Q4 based on the image point Q2 on the second reference picture, P2 determines the object point P4.

Please continue to refer to FIG. 6, an emission light of a dot matrix projector is projected to an object point Q3 on a calibration plate at Znear. The object point Q3 reflects light, and the emitted light forms an image point Q1 on the imaging plane. The one ray is projected to the object point Q4 on the calibration plate at Zfar. The object point Q4 reflects light, and the emitted light forms an image point Q2 on the imaging plane. Another emitting light of the dot matrix projector is projected to the object point P3 on the calibration plate at Znear. The object point P3 reflects light, and the emitted light forms an image point P1 on the imaging plane. The other emitted light is projected onto the object point P4 on the calibration plate at Zfar. The object point P4 reflects light, and the emitted light forms an image point P2 on the imaging plane. Therefore, in the first to third steps of the mobile phone 100, after the mobile phone 100 determines the coordinates of the image points Q1 and P1, it can determine the corresponding object point Q3 according to Q1, determine the corresponding object point P3 according to P1, and determine the corresponding object according to Q2. At point Q4, the corresponding object point P4 is determined according to P2. For example, the mobile phone 100 may calculate the object point coordinates according to the image point coordinates and a preset algorithm, and there may be multiple preset algorithms, such as an inverse perspective imaging algorithm or other algorithms, which are not described in detail in the embodiments of the present application. The following takes the inverse perspective imaging algorithm as an example.

For example, taking Q1 as an example, the mobile phone 100 may determine the object point Q3 corresponding to Q1 according to formula (1).

Z1 * Q1 = P * Q3 Equation (1)

Among them, Q1 is the image point on the first reference picture, that is, in the image plane coordinate system, so the Q1 coordinate is (u1, v1). Z1 is the distance from the object point Q3 to the imaging plane, that is, 20 cm, and P is the conversion formula of the image plane coordinate system to the camera coordinate system:

Among them, f is the focal length of the camera.

Bring the values of the above parameters into formula (1) to get formula (2)

Since the coordinates of Q1 are (u1, v1) and f are known, the coordinates (x1, y1, z1) of the object point Q3 can be determined by formula (2), and the coordinates of this Q3 are the coordinates in the camera coordinate system .

Similarly, the mobile phone 100 can determine the object point P3 corresponding to P1, the object point Q4 corresponding to P2, and the object point P4 corresponding to P2 through the above formula, which is not described in detail here.

In the fifth step, the mobile phone 100 determines a straight line according to Q3 and Q4, determines a straight line according to P3 and P4, and determines the intersection Q of the two straight lines, that is, the virtual optical center of the dot matrix projector 160.

Since Q3, Q4, P3, and P4 are all points obtained in the camera coordinate system, in the fifth step, the virtual optical center of the calibrated dot matrix projector 160 is also a point in the camera coordinate system.

In the above five steps, two image points on the first reference picture and the second reference picture are taken as examples. In fact, the mobile phone 100 can also take a few more points on the first reference picture.

For example, in the above second step, the mobile phone 100 determines 1000 image points on the first reference picture. In the third step, the mobile phone 100 determines 1000 pixels corresponding to the 1000 pixels on the second reference picture. In the fourth step, the mobile phone 100 determines 1000 object points corresponding to the 1000 image points (that is, 1000 object points on the calibration plate at Znear) according to the 1000 image points on the first reference picture. The mobile phone 100 determines 1000 object points corresponding to the 1000 image points (that is, 1000 object points on the calibration plate at Zfar) according to the 1000 image points on the second reference picture. In the fifth step, the mobile phone 100 connects the 1000 object points on the calibration board at Znear obtained in the fourth step with the 1000 object points on the calibration board at Zfar to obtain 1000 straight lines. The intersection points of the 100 straight lines That is, the virtual optical center of the dot matrix projector.

Please refer to FIG. 8, which is a schematic diagram of 1000 rays projected by the dot matrix projector 160. The intersection of these 1000 rays is the virtual optical center of the dot matrix projector 160.

It should be noted that if the intersection point of the 1000 rays is one, the intersection point is the virtual optical center of the dot matrix projector 160. If there are multiple intersections of the 1000 rays (for example, the intersection of two rays is one, and the intersection of the other two rays is another), the mobile phone 100 may determine one of the intersections (for example, at multiple The intersection point at the center of the intersection point) is the virtual light center of the dot matrix projector 160; or, the mobile phone 100 may also have other ways to determine the point based on the multiple intersection points (that is, the virtual light center of the dot matrix projector 160). Examples are not limited.

Please refer to FIG. 9, which is a schematic structural diagram of a dot matrix projector 160 according to an embodiment of the present application. As shown in FIG. 8, a plurality of light emitting points are provided on the dot matrix projector 160 (take 12 as an example in FIG. 8). The process of calibrating the virtual light center shown in FIG. 5 is a process of determining a virtual light center of one light emitting point (for example, light emitting point 1) among a plurality of light emitting points. For other light emitting points, a similar process can be used to calibrate the virtual light center. Each time the mobile phone 100 calibrates a virtual light center of a light emitting point, a plurality of emitted light rays of the light emitting point will be obtained.

As an example, through the process shown in FIG. 5, the mobile phone 100 completes the virtual light center calibration process of a light emitting point of the dot matrix projector 160 and obtains the equation of the emitted light of the light emitting point (such as between Q3 and Q4). Linear equation, linear equation between P3 and P4), the mobile phone 100 can store the virtual optical center coordinates of the light emitting point and the equation of the emitted light for use. It should be noted that, through the process shown in FIG. 5, the determined virtual optical center coordinates and the equations of the emitted light are in the camera coordinate system.

As another example, the mobile phone 100 may not store the equation of the emitted light of the dot matrix projector 160, but store the virtual optical center coordinates of the light emitting points and the coordinates of the calibrated object points. Luminous virtual light center and calibration at a set distance. For example, as described in the previous embodiment, when receiving astigmatism from a dot matrix projector at a set distance (such as Znear), some light spots or spots can be collected, and the coordinates of these spots or spots can be used as a table. The coordinates of the object point in 1. Taking the light-emitting point 1 as an example, the mobile phone 100 can store the virtual light-center coordinates, Q3 and P3 (or Q4, P4) of the light-emitting point 1 correspondingly. Exemplarily, referring to Table 1, the mapping relationship between the virtual optical center coordinates of the light emitting point and the object point coordinates provided by the embodiment of the present application.

Table 1

It should be noted that in Table 1, only the virtual optical center coordinates of the first four light emitting points (light emitting points 1-4) on the dot matrix projector 160 shown in FIG. 9 and the corresponding object points are shown. coordinate. If the mobile phone 100 determines 1000 image points on the first reference picture, corresponding to 1000 object points, then there are 1000 object points corresponding to the light emitting point 1 in Table 1 (only Q3 and P3 objects are used in Table 1). Point for example).

Please continue to refer to FIG. 9, during use of the mobile phone 100, some or all of the multiple light emitting points on the dot matrix projector 160 may be lighted. It should be noted that which light emitting points are illuminated by the mobile phone 100 may be set when the mobile phone 100 leaves the factory. Then different mobile phones have different lighting points, which helps improve the security of each mobile phone. Or, at a certain time (such as the first time), when the distance sensor 180F detects that an object is approaching, the dot matrix projector 160 lights up the first 4 light emitting points, and the light emitted by these 4 light emitting points is projected onto the object, and the object The reflected light is collected by the camera 193 to obtain an image to be verified. At the second moment, when the proximity sensor 180F detects that an object is approaching, the four light-emitting points after the dot-matrix projector 160 lights up, and the light emitted by the latter four light-emitting points is projected onto the object. Get the image to be verified. It can be seen that, when the mobile phone 100 is in use, the light-emitting points that are lit each time may be different, which helps to improve security.

Assume that the mobile phone 100 lights up the first 4 light emitting points this time, because the mobile phone 100 stores the coordinate positions of the light center and the object point of each of the first 4 light emitting points. Therefore, after the mobile phone 100 obtains the image to be verified, it is determined whether the image to be verified is obtained by collecting light reflected on the object from the emission light of the first four light emitting points of the dot matrix projector 160.

Taking a light emitting point as an example, after the mobile phone 100 obtains the image to be verified, the application processor 110-1 runs the code of the face recognition algorithm provided in the embodiment of the present application to perform the process of verifying the image to be verified. Please refer to FIG. 10, which is a schematic flowchart of a face recognition method according to an embodiment of the present application. As shown in FIG. 10, the process of the method includes:

S1001: When the mobile phone 100 is in the lock screen state, when the distance sensor on the mobile phone 100 detects that an object is approaching, the dot matrix projector projects 160 light rays, and the camera 193 collects the light rays to obtain an image to be verified.

In S1001, after the camera 193 obtains the image to be verified, the camera 193 sends the image to be verified to the application processor 110-1 in the mobile phone 100. The application processor 110-1 runs the code of the image correction algorithm provided in the embodiment of the present application to execute as follows S1002-S1005 process.

S1002: Determine an image point E 'on the image to be verified.

The application processor 110-1 may determine any one image point on the image to be verified, that is, E '. The image point E 'is a point of the image plane coordinate system.

S1003: Determine whether the object point E corresponding to the image point E 'is on the light emitted from the virtual light center of the dot matrix projector. If yes, execute S1004; if not, execute S1005.

The application processor 110-1 may determine the object point E corresponding to the image point E 'according to the foregoing formula (1), and obtain that the object point E is a point in the camera coordinate system.

If the mobile phone 100 stores the virtual light center of each luminous point and the equation of the emitted light of the luminous point, the application processor 110-1 determines whether the object point E is in the equation of the emitted light of the luminous point. .

If the mobile phone 100 stores the coordinates of the virtual light center of each luminous point and the corresponding object point (for example, Table 1), the application processor 110-1 may according to the virtual light center and multiple object points corresponding to the virtual light center. Coordinates determine multiple straight lines (since the virtual optical center and the object point are both points in the camera coordinate system, the multiple straight lines obtained are also straight lines in the camera coordinate system). The application processor 110-1 determines whether the object point E is on a certain straight line among the plurality of straight lines. If yes, it means that the image to be verified is obtained by collecting the light reflected on the object by the emission light from the dot matrix projector 160. If not, it means that the image to be verified is obtained by collecting the light reflected on the object by the light emitted from the dot matrix projector 160.

It should be noted that, as can be seen from the foregoing, all or part of the light emitting points in the dot matrix projector 160 can emit light. Therefore, in practical applications, the mobile phone 100 can set a logo for each light emitting point. When a certain light emitting point is lighted, the application processor 110-1 determines the identification of the lighted light emitting point (mode one, which light point is lit is determined by the application processor 110-1, so the application processor 110 -1 knows the identification of the illuminated light point. In the second way, the lighting of that light point is determined by the dot matrix projector 160. Which dot is illuminated by the dot matrix projector 160 sends the identification of the light point to the application. Processor 110-1). The application processor 110-1 determines the virtual optical center coordinates of the light-emitting point according to Table 2. If there are multiple lighting points, the application processor 110-1 may determine the virtual light center of each lighting point and the corresponding object point. Taking the light emitting point 1 as an example, the application processor 110-1 determines that the virtual light center of the light emitting point 1 is A and a plurality of object points corresponding to the virtual light center A according to Table 1. The application processor 110-1 may determine a plurality of straight lines according to the coordinates of the virtual light center A and a plurality of object points corresponding to the virtual light center A.

It should be noted that the virtual optical centers of the luminous points 1-4 in Table 1 and the object points corresponding to each virtual optical center are in the camera coordinate system. In practical applications, the mobile phone 100 can convert the virtual light center and the object point corresponding to each virtual light center into the world coordinate system, which is not limited in the embodiment of the present application. If the virtual light centers in Table 1 and the object points corresponding to each virtual light center are points in the actual coordinate system, then in the subsequent process of using the mobile phone 100, after the mobile phone 100 captures the image to be verified, the image to be verified will be The upper image point E 'is converted into the world coordinate system. In short, the application processor 110-1 may convert the coordinate system of the image point E ′ on the image to be verified to the same coordinate system as the virtual optical center and the object point in Table 1. Or, the application processor 110-1 may The image point E 'on the image to be verified can be converted into the same coordinate system as the emitted light of the light emitting point.

Optionally, it can be known from the foregoing that the image sensor in the camera 193 captures the first reference picture and the second reference picture. Because the image sensor will be affected by temperature changes when acquiring images, that is, the temperature drift phenomenon, resulting in errors in the virtual optical center coordinates and object point coordinates obtained during the virtual optical center calibration process of the mobile phone 100. Therefore, the mobile phone 100 may perform temperature drift compensation on a virtual optical center and an object point corresponding to the virtual optical center before using a virtual optical center and an object point corresponding to the virtual optical center in Table 1 to obtain a pass. The coordinates of the virtual optical center after temperature drift compensation and the object point corresponding to the virtual optical center are then executed as shown in FIG. 10 or FIG. 12. Among them, the temperature drift compensation method may have multiple thermal compensation methods or non-thermal component compensation methods, etc., which are not limited in the embodiments of the present application.

S1004: Determine whether the image to be verified is consistent with a pre-stored face image, and if they are consistent, unlock the device, and if not, do not respond to the image to be verified.

Optionally, if the mobile phone 100 is in the lock screen and the black screen, the unlocking device may be that the mobile phone 100 is lit by the black screen and displays the main interface. If the mobile phone 100 is locked and bright, the unlocking device is that the mobile phone 100 switches from the lock screen interface to the main interface.

S1005: Output a prompt message, which is used to prompt the user that the image to be verified is obtained by collecting the light reflected on the object from the emitted light of the dot matrix projector 160, which poses a security risk.

For example, the prompt information may be text information or icon information displayed on the display screen 194, or voice information played by a speaker. To improve security, the mobile phone 100 may automatically delete the image to be verified.

It should be noted that, in the process shown in FIG. 10, an image point E 'on the image to be verified is taken as an example. In an actual application, the application processor 110-1 may select N image points on the image to be verified (for example, determine the N image points on the image to be verified in S1002). For each of the N image points, S1003 can be performed once. Optionally, when the application processor 110-1 determines that among the N object points corresponding to the N image points, the number of object points on the emission light of the light emitting point is greater than a preset number, the application processor 110-1 executes S1004 .

It should be noted that, before the light emitted by the dot matrix projector 160 is projected onto an object, it may pass through optical elements such as diffractive optical elements (DOE). The optical element diffracts the emitted light from the dot matrix projector 160 to form a diffracted light spot. For example, please refer to FIG. 11, which is a diffracted light spot formed after being diffracted by an optical element. The diffracted light spot is projected on the human face, and the camera 193 collects the reflected light of the diffracted light spot on the object to obtain an image to be verified. Generally, among the diffracted light spots formed by optical diffraction, the 0th order is at the center position of the diffracted light spot, and the 1st order, the 2nd order, and the like from the center position to the edge position. Therefore, the center position on the to-be-verified image captured by the mobile phone 100 is level 0, and the order from the center position to the edge position is level 1, level 2, and so on. Therefore, when the mobile phone 100 selects an image point on the image to be verified, it may first take a certain image point at the center position, that is, level 0, on the image to be verified, and then execute S1003. When the mobile phone 100 executes S1003 and determines that the object point corresponding to the image point of level 0 is not on the emission light of the dot matrix projector 160, the mobile phone 100 may determine other image points of level 0 again, and then execute S1003. If the number of object points on the emission light of the dot matrix projector 160 among multiple object points corresponding to multiple image points of level 0 is greater than a preset number, the mobile phone 100 determines that the image to be verified is collected by the dot matrix projector 160 Resulting from the rays of light reflected on an object. Alternatively, the mobile phone 100 may continue to determine the image point on level 1 and then execute S1003. When the mobile phone 100 determines that the number of the object points on the light emitted by the dot matrix projector 160 among the multiple object points corresponding to the multiple image points on the 0-1 level is greater than a preset number, the mobile phone 100 determines that the image to be verified is collected by The light emitted from the dot matrix projector 160 is obtained by the light reflected on the object.

It should be noted that, in the embodiment shown in FIG. 10, the application processor 110-1 first determines whether the image to be verified is obtained by collecting light reflected on the object by the emission light of the dot matrix projector 160, and if so, determines Whether the image to be verified matches the pre-stored face image. In fact, the execution order between the above processes can be adjusted, that is, the application processor 110-1 first determines whether the image to be verified matches the pre-stored face image, and when the image to be verified matches the pre-stored image, the process is then determined Whether the image is obtained by collecting the light reflected by the emitted light from the dot matrix projector 160 on the object. Please refer to FIG. 12, the process is as follows:

S1201: When the mobile phone 100 is in the lock screen state, when the distance sensor on the mobile phone 100 detects that an object is approaching, the dot matrix projector projects light, and the camera collects light to obtain an image to be verified.

In S1201, after the camera obtains the image to be verified, the camera sends the image to be verified to the application processor 110-1 in the mobile phone 100. The application processor 110-1 runs the code of the image correction algorithm provided in the embodiment of the present application to execute the following S1202 -S1205 process.

S1202: Determine whether the image to be verified is consistent with the pre-stored face image. If they are consistent, execute S1203. If they are not consistent, do not respond to the image to be verified.

Virtual light center S1203: Determine an image point E 'on the image to be verified.

S1204: Determine whether the object point E corresponding to the image point E 'is on the light emitted from the virtual optical center of the dot matrix projector. If yes, unlock the device; if not, execute S1205.

S1205: Output a prompt message, which is used to prompt the user that the image to be verified is not obtained by collecting the light reflected on the object from the light emitted by the dot matrix projector 160, which poses a security risk.

In the foregoing embodiment, the scenario of unlocking the device through face recognition is taken as an example. In fact, the face recognition algorithm provided in the embodiments of the present application can also be applied to other scenarios, such as face-brush payment (for example, the mobile phone 100 displays a payment interface, and executes the payment process when the image verification to be verified passes; , Do not execute the payment process), face punch, password, or permission settings (such as the phone 100 display permission or password setting interface, when the image to be verified passes the authorization or password setting operation, when the image to be verified fails, Perform permissions or password setting operations) and other similar scenarios. It should be noted that, in the embodiment of the present application, a trigger condition for triggering face recognition (such as a proximity sensor detecting an object approaching or other conditions), a process of acquiring an image to be verified (that is, a face image), and The process of matching the image with the pre-stored face image, the process after the image to be verified is successfully processed, or the process after the image to be verified fails, may refer to related implementations in the prior art. The specific implementation is not limited.

In summary, the face recognition method provided in the embodiment of the present application can determine whether the image to be verified (that is, the face image) is obtained by collecting the light reflected on the object by the light emitted by the local dot matrix projector 160. In this way, it is possible to prevent hackers from inputting other face images (not images obtained by collecting the light reflected by the emitted light of the machine on the object) into the mobile phone for verification. Such a face recognition method has high security. Further, the face recognition method provided in the embodiment of the present application is implemented based on the basic optical imaging principle, the scheme is simple, the calculation amount is small, it is helpful to receive the calculation amount, and improve the efficiency.

It should be noted that the face recognition method provided in the embodiment of the present application may be a default function of the mobile phone 100, that is, after the user activates the mobile phone 100, the mobile phone 100 automatically performs face recognition using the face recognition method provided in the embodiment of the present application. . Alternatively, the face recognition method may be set by the user, that is, when the user uses the mobile phone 100, the face recognition mode of the mobile phone 100 is set to the face recognition mode provided in the embodiment of the application. Alternatively, some steps in the face recognition method are set by a user, and some steps are defaulted by the mobile phone 100. For example, taking FIG. 10 as an example, the mobile phone 100 in FIG. 10 executes only S1004 by default, and does not execute S1001-S1003. When the user activates this function (a function of detecting whether a face image is generated by light projected by the machine), when the mobile phone 100 recognizes a face, S1001-S1005 is performed.

Exemplarily, please refer to FIG. 13, which is a schematic diagram of an interface of a mobile phone setting application according to an embodiment of the present application.

As shown in (a) of FIG. 13, the mobile phone 100 displays a setting interface 1301 of a setting application, and the setting interface 1301 includes a password setting option 1302. After the user activates the password setting option 1302, the display interface of the mobile phone 100 is as shown in FIG. 13 (b). The mobile phone 100 displays an interface 1303 of the password setting option 1302, and the interface 1303 includes a graphic password, a digital password, a fingerprint password, and a face password. When the face password option 1304 is activated, the interface of the mobile phone 100 is as shown in (c) of FIG. 13. The mobile phone 100 displays a face password setting interface 1305, and the interface 1305 includes only two options of face matching and local light emission determination. When the user activates the control 1306 corresponding to face matching only, the mobile phone 100 only compares the face image with the stored face image. If they are the same, the authentication is passed, and if they are not, the authentication is not passed. When the user activates the local light emission to determine the corresponding control 1307, the mobile phone 100 executes the process shown in FIG. 10 or FIG. 12 again.

Various embodiments of the present application can be arbitrarily combined to achieve different technical effects.

In the embodiment provided by the present application, the method provided by the embodiment of the present application is described from the perspective of the terminal (the mobile phone 100) as the execution subject. In order to implement the functions in the method provided by the embodiments of the present application, the terminal may include a hardware structure and / or a software module, and implement the foregoing functions in the form of a hardware structure, a software module, or a hardware structure and a software module. Whether one of the above functions is executed by a hardware structure, a software module, or a hardware structure plus a software module depends on the specific application of the technical solution and design constraints.

Based on the same concept, FIG. 14 illustrates a terminal 1400 provided by the present application. As shown in FIG. 14, the terminal 1400 may include a dot matrix projector 1401, a camera 1402, one or more processors 1403, a memory 1404, and one or more computer programs 1405. The communication bus 1406 is connected.

Among them, the dot matrix projector 1401 is used to project light (all or part of the light emitting points on the dot matrix projector 1401 are used to project light), and the camera 1402 is used to collect images (the image to be verified, the first reference picture or the second reference picture); The one or more computer programs 1405 are stored in the memory 1404 and configured to be executed by the one or more processors 1403. The one or more computer programs 1405 include instructions, and the foregoing instructions may be used to execute All or part of the steps shown in FIG. 5 and each step in the corresponding embodiment; or, S1002-S1005 shown in FIG. 10 and each step in the corresponding embodiment are performed; or S1202-S1205 and Each step in the corresponding embodiment.

An embodiment of the present invention further provides a computer storage medium. The storage medium may include a memory, and the memory may store a program. When the program is executed, the execution of the terminal includes the previous execution, as shown in FIG. 5, FIG. 10, and FIG. All or part of the steps performed by the terminal described in the method embodiment shown in 12.

An embodiment of the present invention further provides a computer program product that, when the computer program product runs on a terminal, causes the terminal to execute a method including the method described in the previous embodiments shown in FIG. 5, FIG. 10, and FIG. All or part of the steps performed by the terminal.

Through the description of the foregoing implementation manners, those skilled in the art can clearly understand that the embodiments of the present application can be implemented by hardware, firmware, or a combination thereof. When implemented in software, the functions described above may be stored in a computer-readable medium or transmitted as one or more instructions or code on a computer-readable medium. Computer-readable media includes computer storage media and communication media including any medium that facilitates transfer of a computer program from one place to another. A storage media may be any available media that can be accessed by a computer. Take this as an example but not limited to: computer-readable media may include RAM, ROM, electrically erasable programmable read-only memory (EEPROM), read-only memory (EEPROM), compact disc-read-only memory (CD-ROM) ROM) or other optical disk storage, magnetic disk storage media or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and can be accessed by a computer. Also. Any connection is properly a computer-readable medium. For example, if the software is transmitted from a website, server, or other remote source using coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL), or wireless technology such as infrared, radio, and microwave, Then coaxial cables, fiber optic cables, twisted pairs, DSL, or wireless technologies such as infrared, wireless, and microwave are included in the fixing of the media. As used in the embodiments of the present application, disks and discs include compact discs (CDs), laser discs, optical discs, digital video discs (DVDs), floppy discs, and Blu-ray discs, among which Discs usually reproduce data magnetically, while discs use lasers to reproduce data optically. The above combination should also be included in the protection scope of the computer-readable medium.

In short, the above is only an embodiment of the present application, and is not intended to limit the protection scope of the present application. Any modification, equivalent replacement, improvement, etc. made according to the disclosure of this application shall be included in the protection scope of this application.

Claims

A face recognition method, comprising:

A dot matrix projector on the terminal emits light, and a camera on the terminal collects an image to be verified;

Determining, by the terminal, N first image points on the image to be verified; N is an integer greater than or equal to 1;

Determining, by the terminal, N first object points corresponding to the N first image points according to the N first image points and parameters of the camera;

Determining, by the terminal, whether the N first object points are on the emission light of the dot matrix projector;

If the N first object points are on the emission light of the dot matrix projector, the terminal determines whether the image to be verified is consistent with a pre-stored face image;

If the image to be verified is consistent with a pre-stored face image, the terminal determines that the face recognition is successful.
The method according to claim 1, wherein before the terminal determines whether the N first object points are on the emission light of the dot matrix projector, the method further comprises:

The J-th light emitting point among the K light emitting points of the dot matrix projector emits light, K is an integer greater than or equal to 1, J is an integer less than or equal to K, and greater than or equal to 1;

The camera on the terminal collects a first reference picture and a second reference picture; the first reference picture is obtained by the terminal collecting objects at a first distance from the terminal, and the second reference picture is the Obtained by the terminal collecting the object at a second distance; the second distance is greater than the first distance;

The terminal selects M second image points on the first reference picture, where M is an integer greater than or equal to 2;

Determining, by the terminal according to the M second image points and the matching algorithm, M third image points on the second reference picture that are one-to-one matched with each of the M second image points, Wherein, the P-th second image point matches the P-th third image point, and P is an integer greater than or equal to 1 and less than or equal to M;

The terminal determines corresponding M second object points according to the M second image points and parameters of the camera, and determines corresponding M third objects according to the M third image points and parameters of the camera. An object point, wherein the P-th second object point matches the P-th third object point;

The terminal calculates coordinates of a virtual light center of the Jth light emitting point of the dot matrix transmitter, the virtual light center is obtained by intersecting M first straight lines, and the Pth second object point and the The P-th third object point is connected to obtain the first straight line.
The method according to claim 1, wherein before the terminal determines whether the N first object points are on the emission light of the dot matrix projector, the method further comprises:

The J-th light emitting point among the K light emitting points of the dot matrix projector emits light, K is an integer greater than or equal to 1, J is an integer less than or equal to K, and greater than or equal to 1;

The camera on the terminal collects a first reference picture and a second reference picture; the first reference picture is obtained by the terminal collecting objects at a first distance from the terminal, and the second reference picture is the Obtained by collecting the object at a second distance; the second distance is greater than the first distance;

The terminal selects M second image points on the first reference picture, where M is an integer greater than or equal to 2;

Determining, by the terminal according to the M second image points and the matching algorithm, M third image points on the second reference picture that are one-to-one matched with each of the M second image points, Wherein, the P-th second image point matches the P-th third image point, and P is an integer greater than or equal to 1 and less than or equal to M;

The terminal determines corresponding M second object points according to the M second image points and parameters of the camera, and determines corresponding M third objects according to the M third image points and parameters of the camera. An object point, wherein the P-th second object point matches the P-th third object point;

The terminal calculates coordinates of a virtual light center of the Jth light emitting point of the dot matrix transmitter, where the virtual light center is obtained by the intersection of M first straight lines, and the P second second object after temperature drift compensation. A point is connected to the P-th third object point after temperature drift compensation to obtain the first straight line.
The method according to claim 2 or 3, wherein the terminal determining whether the N first object points are on the emission light of the dot matrix projector comprises:

The terminal determines whether the N first object points are on the emission light of the K light emitting points according to the coordinates of the K virtual light centers of the dot matrix transmitter and the equation of K * M emission light.
The method according to claim 2 or 3, wherein the terminal determining whether the N first object points are on the emission light of the dot matrix projector comprises:

Determining, by the terminal according to the coordinates of the K virtual light centers and the coordinates of the calibrated object points, whether the N first object points are in the connection between the K virtual light centers and the calibrated object points If it is on at least one of the lines, if it is on at least one of the K lines, then it is determined that the N first object points are on the emission light of the dot matrix projector, and if it is not on the K lines, On at least one of the lines, it is determined that the N first object points are not on the emission light of the dot matrix projector.
The method according to any one of claims 1 to 5, wherein the dot matrix projector on the terminal emits light, and before the camera on the terminal collects the image to be verified, the method further comprises:

The terminal is in a lock screen state;

After the terminal determines that the face recognition is successful, the method further includes: unlocking the terminal.
The method according to any one of claims 1 to 5, wherein the dot matrix projector on the terminal emits light, and before the camera on the terminal collects the image to be verified, the method further comprises:

The terminal displays a payment verification interface;

After the terminal determines that the face recognition is successful, the method further includes that the terminal executes a payment process.
The method according to any one of claims 1 to 5, wherein the dot matrix projector on the terminal emits light, and before the camera on the terminal collects the image to be verified, the method further comprises:

The terminal displays a permission or password setting interface;

After the terminal determines that the face recognition is successful, the method further includes that the terminal performs a permission or password setting operation.
The method according to any one of claims 1 to 8, wherein if the image to be verified is not consistent with a pre-stored face image, the terminal determines that face recognition has failed.
An optical center calibration method, characterized in that the method includes:

The Kth light emitting point among the K light emitting points of the dot matrix projector on the terminal emits light, K is an integer greater than or equal to 1, J is an integer less than or equal to K, and greater than or equal to 1;

The camera on the terminal collects a first reference picture and a second reference picture; the first reference picture is obtained by the terminal collecting objects at a first distance from the terminal, and the second reference picture is the Obtained by collecting the object at a second distance; the second distance is greater than the first distance;

The terminal selects M second image points on the first reference picture, where M is an integer greater than or equal to 2;

Determining, by the terminal according to the M second image points and the matching algorithm, M third image points on the second reference picture that are one-to-one matched with each of the M second image points, Wherein, the P-th second image point matches the P-th third image point, and P is an integer greater than or equal to 1 and less than or equal to M;

The terminal determines corresponding M second object points according to the M second image points and parameters of the camera, and determines corresponding M third objects according to the M third image points and parameters of the camera. An object point, wherein the P-th second object point matches the P-th third object point;

The terminal calculates coordinates of a virtual light center of the Jth light emitting point of the dot matrix transmitter, the virtual light center is obtained by intersecting M first straight lines, and the Pth second object point and the The P-th third object point is connected to obtain the first straight line.
A terminal characterized by comprising a dot matrix projector, a camera, a processor and a memory;

The dot matrix projector: for emitting light;

The camera is used to collect an image to be verified;

The memory is configured to store one or more computer programs; when the one or more computer programs stored in the memory are executed by the processor, the terminal is caused to execute:

Determining N first image points on the image to be verified; N is an integer greater than or equal to 1;

Determining N first object points corresponding to the N first image points according to the N first image points and parameters of the camera;

Determining whether the N first object points are on the emission light of the dot matrix projector;

If the N first object points are on the emission light of the dot matrix projector, determine whether the image to be verified is consistent with a pre-stored face image;

If the image to be verified is consistent with a pre-stored face image, it is determined that the face recognition is successful.
The terminal according to claim 11, wherein the Jth light emitting point among the K light emitting points of the dot matrix projector emits light, K is an integer greater than or equal to 1, J is less than or equal to K, and is greater than or equal to An integer of 1

The camera is further configured to collect a first reference picture and a second reference picture; the first reference picture is obtained by collecting an object at a first distance from the terminal, and the second reference picture is collected at a second Obtained from the object at a distance; the second distance is greater than the first distance;

When the one or more computer programs stored in the memory are executed by the processor, the terminal is further caused to execute:

Selecting M second image points on the first reference picture, where M is an integer greater than or equal to 2;

According to the M second image points and the matching algorithm, M third image points on the second reference picture that are matched one by one with each second image point of the M second image points, respectively, P second image points match the Pth third image point, and P is an integer greater than or equal to 1 and less than or equal to M;

Determining corresponding M second object points according to the M second image points and parameters of the camera, and determining corresponding M third object points according to the M third image points and parameters of the camera, Wherein, the P-th second object point matches the P-th third object point;

Calculate the coordinates of the virtual light center of the Jth light emitting point of the dot matrix emitter, the virtual light center is obtained by the intersection of M first straight lines, the Pth second object point and the Pth The third object point is connected to obtain the first straight line.
The terminal according to claim 11, wherein the Jth light emitting point among the K light emitting points of the dot matrix projector emits light, K is an integer greater than or equal to 1, J is less than or equal to K, and is greater than or equal to An integer of 1

The camera is further configured to collect a first reference picture and a second reference picture; the first reference picture is obtained by collecting an object at a first distance from the terminal, and the second reference picture is collected at a second Obtained from the object at a distance; the second distance is greater than the first distance;

When the one or more computer programs stored in the memory are executed by the processor, the terminal is further caused to execute:

Selecting M second image points on the first reference picture, where M is an integer greater than or equal to 2;

According to the M second image points and the matching algorithm, M third image points on the second reference picture that are matched one by one with each second image point of the M second image points, respectively, P second image points match the Pth third image point, and P is an integer greater than or equal to 1 and less than or equal to M;

Determining corresponding M second object points according to the M second image points and parameters of the camera, and determining corresponding M third object points according to the M third image points and parameters of the camera, Wherein, the P-th second object point matches the P-th third object point;

Calculate the coordinates of the virtual light center of the J-th light emitting point of the dot matrix transmitter, the virtual light center is obtained by the intersection of M first straight lines, and the P-th second object point and The P-th third object point after temperature drift compensation is connected to obtain the first straight line.
The terminal according to claim 12 or 13, wherein when one or more computer programs stored in the memory are executed by the processor, the terminal is further caused to execute:

According to the coordinates of the K virtual light centers of the dot matrix transmitter and the equation of K * M emitted light, it is determined whether the N first object points are on the emitted light of the K light emitting points.
The terminal according to claim 12 or 13, wherein when one or more computer programs stored in the memory are executed by the processor, the terminal is further caused to execute:

Determine whether the N first object points are in a line connecting the K virtual optical centers and the calibrated object points according to the coordinates of the K virtual optical centers and the coordinates of the calibrated object points On at least one, if it is on at least one of the K lines, it is determined that the N first object points are on the emission light of the dot matrix projector, and if it is not on the K lines, It is determined that at least one of the N first object points is not on the emission light of the dot matrix projector.
The terminal according to any one of claims 11 to 15, wherein before the dot matrix projector emits light, the terminal is in a lock screen state; when one or more computer programs stored in the memory are deleted by When the processor executes, the terminal is further caused to execute: after determining that the face recognition is successful, unlock the terminal.
The terminal according to any one of claims 11 to 15, wherein the terminal further comprises a display screen, and before the dot matrix projector emits light, the display screen displays a payment verification interface; when the memory stores When the one or more computer programs are executed by the processor, the terminal is further caused to execute: after determining that the face recognition is successful, execute a payment process.
The terminal according to any one of claims 11 to 15, wherein the terminal further comprises a display screen, and before the dot matrix projector emits light, the display screen displays a permission or password setting interface; when the When the one or more computer programs stored in the memory are executed by the processor, the terminal is further caused to execute: after determining that the face recognition is successful, perform a permission or password setting operation.
The terminal according to any one of claims 11 to 18, wherein when the one or more computer programs stored in the memory are executed by the processor, the terminal is further caused to execute:

If the image to be verified is inconsistent with a pre-stored face image, it is determined that face recognition has failed.
A terminal characterized by comprising a dot matrix projector, a camera, a processor and a memory;

The J-th light emitting point among the K light emitting points of the dot matrix projector emits light, K is an integer greater than or equal to 1, J is an integer less than or equal to K, and greater than or equal to 1;

The camera is used to collect a first reference picture and a second reference picture; the first reference picture is obtained by the terminal collecting objects at a first distance from the terminal, and the second reference picture is the acquisition Obtained by the object at a second distance; the second distance is greater than the first distance;

The memory is configured to store one or more computer programs; when the one or more computer programs stored in the memory are executed by the processor, the terminal is caused to execute:

Selecting M second image points on the first reference picture, where M is an integer greater than or equal to 2;

According to the M second image points and the matching algorithm, M third image points on the second reference picture that are matched one by one with each second image point of the M second image points, respectively, P second image points match the Pth third image point, and P is an integer greater than or equal to 1 and less than or equal to M;

Determining corresponding M second object points according to the M second image points and parameters of the camera, and determining corresponding M third object points according to the M third image points and parameters of the camera, Wherein, the P-th second object point matches the P-th third object point;

Calculate the coordinates of the virtual light center of the Jth light emitting point of the dot matrix emitter, the virtual light center is obtained by the intersection of M first straight lines, the Pth second object point and the Pth The third object point is connected to obtain the first straight line.
A computer storage medium, wherein the computer-readable storage medium includes a computer program, and when the computer program runs on a terminal, the terminal causes the terminal to execute the method according to any one of claims 1 to 10.
A computer program product containing instructions, wherein when the instructions are run on a computer, the computer is caused to execute the method according to any one of claims 1-10.