Touch screen visual error compensation method and device, electronic equipment and storage medium
By determining visual error distances based on finger and eye positions and angles, the method compensates for inaccuracies in touch screen interactions, enhancing accuracy and preventing misoperations.
Patent Information
- Application Number
- CN202411192029.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-28
- Publication Date
- 2024-12-03
AI Technical Summary
The inconsistency between the user's click intention and the actual response position on a touch screen due to factors such as finger size and visual errors leads to inaccurate operations, potentially causing misoperations in critical situations.
A method and device that acquire terminal ellipse parameters of the touching finger, relative position coordinates of the user's eyes and finger, and angles between them to determine a visual error distance, allowing for error compensation on the touch screen by simulating the end knuckle of the finger as an elliptical shape to improve accuracy.
The method enhances the accuracy of touch screen operations by reducing errors caused by finger and angle discrepancies, ensuring the actual response position aligns closer to the user's intended click, thereby improving user experience and preventing misoperations.
Smart Images

Figure CN119065580A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of error compensation, and in particular to a touch screen visual error compensation method, device, electronic device and storage medium. Background Art
[0002] Driven by digital technology, mobile electronic devices, especially mobile phones, have penetrated into every corner of daily life, bringing great convenience to people's daily lives. Whether it is to quickly find information, communicate, or entertain and shop, it can be achieved anytime, anywhere, just by touching the touch screen. However, while enjoying the convenience brought by technology, people are also facing a problem that cannot be ignored: when touching the screen with a finger, due to factors such as the size of the finger and visual errors, the click intention and the actual response position are often inconsistent, making the operation not as accurate and effective as expected. This seemingly minor problem not only affects the user experience, but may also cause misoperation at critical moments, resulting in more serious situations such as the incorrect sending of important information. Summary of the invention
[0003] The present application provides a touch screen visual error compensation method, device, electronic device and storage medium to solve the problem of how to improve the accuracy of the touch screen.
[0004] In a first aspect, the present application provides a touch screen visual error compensation method, the method comprising:
[0005] Acquire the terminal ellipse parameters of the target object's touching finger; wherein the touching finger is the finger of the target object touching the touch screen, and the terminal ellipse parameters include the horizontal radius and the vertical radius of the ellipse shape equivalent to the terminal knuckle of the touching finger;
[0006] Acquire the relative position coordinates of the target object's eyes and the touching finger;
[0007] Acquire a first angle between the touching finger and the touch screen;
[0008] Determine a second angle between the eye of the target object and the touch screen according to the relative position coordinates;
[0009] Determine a visual error distance according to the first angle, the horizontal radius, the vertical radius and the second angle;
[0010] Error compensation is performed on an actual touch point of the touch screen touched by the touching finger according to the visual error distance.
[0011] Optionally, obtaining the end ellipse parameters of the touching finger of the target object includes:
[0012] Obtaining input terminal ellipse parameters of the touching finger;
[0013] or,
[0014] Acquire a finger image of the target object's touching finger captured by a camera; and calculate the terminal ellipse parameters according to the finger image and a preset calculation model.
[0015] Optionally, obtaining the relative position coordinates of the target object's eyes and the touching finger includes:
[0016] Determine a spatial coordinate system based on a camera of a terminal where the touch screen is located;
[0017] Acquire the first spatial coordinate of the actual touch point in the spatial coordinate system;
[0018] Acquire the second spatial coordinates of the eye of the target object captured by the camera in the spatial coordinate system;
[0019] The relative position coordinates are determined according to the first space coordinates and the second space coordinates.
[0020] Optionally, obtaining a first angle between the touching finger and the touch screen includes:
[0021] Acquire an interactive image of the touch finger touching the touch screen; determine the first angle according to the interactive image;
[0022] or,
[0023] Obtain a target contact area between the touching finger and the touch screen when the touching finger touches the touch screen; determine the first angle according to the target contact area and a preset mapping relationship; wherein the mapping relationship is a mapping relationship between the contact area and the finger-screen angle; and the target contact area is negatively correlated with the first angle.
[0024] Optionally, determining a second angle between the eye of the target object and the touch screen according to the relative position coordinates includes:
[0025] Determining a third angle between the eye of the target object and the vertical axis direction of the touch screen according to the Y-axis coordinate of the relative position coordinate and the Z-axis coordinate of the relative position coordinate;
[0026] Determining a fourth angle between the eye of the target object and the horizontal axis direction of the touch screen according to the X-axis coordinate of the relative position coordinate and the Z-axis coordinate of the relative position coordinate;
[0027] The third angle and the fourth angle are used as a second angle between the eye of the target object and the touch screen.
[0028] Optionally, determining the visual error distance according to the first angle, the horizontal radius, the vertical radius and the second angle includes:
[0029] Determine a first distance between the focus of the equivalent elliptical shape and the center point of the equivalent elliptical shape according to the horizontal radius and the vertical radius;
[0030] determining a vertical axis deviation according to the first distance, the first angle, and the third angle;
[0031] Determine a horizontal axis deviation according to the first distance, the first angle, and the fourth angle;
[0032] The vertical axis deviation and the horizontal axis deviation are used as the visual error distance.
[0033] Optionally, performing error compensation on an actual touch point of the touch screen touched by the touching finger according to the visual error distance includes:
[0034] Acquire the vertical coordinate of the actual touch point and the horizontal coordinate of the actual touch point;
[0035] Compensating the vertical coordinate of the actual touch point according to the vertical axis deviation;
[0036] The horizontal coordinate of the actual touch point is compensated according to the horizontal axis deviation.
[0037] Optionally, obtaining the second spatial coordinates of the eye of the target object captured by the camera in the spatial coordinate system includes:
[0038] Acquire a head image of the target object captured by the camera;
[0039] Determine the left eye coordinates and the right eye coordinates of the target object in the spatial coordinate system based on the head image;
[0040] Determine the second spatial coordinates of the eye of the target object in the spatial coordinate system according to the left eye coordinates and the right eye coordinates.
[0041] Optionally, obtaining the first spatial coordinate of the actual touch point in the spatial coordinate system includes:
[0042] Acquire the actual touch point of the touch screen touched by the touching finger;
[0043] The first spatial coordinate of the actual touch point in the spatial coordinate system is determined according to the actual touch point, the screen resolution of the touch screen, and the screen size of the touch screen.
[0044] In a second aspect, the present application provides a touch screen visual error compensation device, the device comprising:
[0045] A first acquisition module is used to acquire terminal ellipse parameters of a touching finger of a target object; wherein the touching finger is a finger of the target object touching the touch screen, and the terminal ellipse parameters include a horizontal radius and a vertical radius of an ellipse shape equivalent to a terminal knuckle of the touching finger;
[0046] A second acquisition module, used to acquire the relative position coordinates of the target object's eyes and the touching finger;
[0047] A third acquisition module, used to acquire a first angle between the touching finger and the touch screen;
[0048] A first determining module, configured to determine a second angle between the eye of the target object and the touch screen according to the relative position coordinates;
[0049] A second determination module, configured to determine a visual error distance according to the first angle, the horizontal radius, the vertical radius and the second angle;
[0050] The error compensation module is used to perform error compensation on the actual touch point of the touch screen touched by the touch finger according to the visual error distance.
[0051] In a third aspect, the present application provides an electronic device, including a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other via the communication bus;
[0052] Memory, used to store computer programs;
[0053] The processor is used to implement the touch screen visual error compensation method described in any embodiment of the first aspect when executing the program stored in the memory.
[0054] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the touch screen visual error compensation method as described in any embodiment of the first aspect is implemented.
[0055] The above technical solution provided by the embodiment of the present application has the following advantages over the prior art: the method provided by the embodiment of the present application obtains the terminal ellipse parameters of the touching finger of the target object; wherein the touching finger is the finger of the target object touching the touch screen, and the terminal ellipse parameters include the horizontal radius and the vertical radius of the ellipse shape equivalent to the terminal knuckle of the touching finger; obtains the relative position coordinates of the eye of the target object and the touching finger; obtains the first angle between the touching finger and the touch screen; determines the second angle between the eye of the target object and the touch screen according to the relative position coordinates; determines the visual error distance according to the first angle, the horizontal radius, the vertical radius and the second angle; and performs error compensation on the actual touch point where the touching finger touches the touch screen according to the visual error distance. The method converts the end knuckle of a touching finger into an elliptical shape, obtains a first angle between the touching finger and the touch screen, determines a second angle between the eyes of a target object and the touch screen, and determines a visual error distance according to the first angle, the second angle, and the horizontal radius and the vertical radius of the equivalent elliptical shape. According to the visual error distance, error compensation is performed on the actual touching point, thereby reducing the error caused by the first angle and the second angle. At the same time, the end knuckle of an actual touching touch screen is more accurately simulated by combining the equivalent ellipsoid shape, so that the actual response position of the touch screen is closer to the actual clicking intention of the target object, thereby improving the clicking accuracy of the user when using the touch screen. BRIEF DESCRIPTION OF THE DRAWINGS
[0056] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.
[0057] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.
[0058] One or more embodiments are exemplarily described by pictures in the corresponding drawings, and these exemplified descriptions do not constitute limitations on the embodiments. Elements with the same reference numerals in the drawings represent similar elements, and unless otherwise stated, the figures in the drawings do not constitute proportional limitations.
[0059] Figure 1 A system architecture diagram of a touch screen visual error compensation method provided by one embodiment of the present application;
[0060] Figure 2 A schematic diagram of a flow chart of a touch screen visual error compensation method provided by an embodiment of the present application;
[0061] Figure 3 A system block diagram of a touch screen visual error compensation method provided by one embodiment of the present application;
[0062] Figure 4 A schematic diagram of the angle between the end of a finger and the screen provided in one embodiment of the present application;
[0063] Figure 5 A schematic diagram of the angle between an eye and a screen provided in one embodiment of the present application;
[0064] Figure 6 A schematic diagram of the relative positions of a finger touch position and an eye position in a spatial coordinate system provided for one embodiment of the present application;
[0065] Figure 7 A schematic diagram of a vertical radius and a horizontal radius for calculating terminal ellipse parameters provided in one embodiment of the present application;
[0066] Figure 8 A schematic diagram of visual error distance between a finger and a screen at different angles provided by an embodiment of the present application;
[0067] Fig. 9 A schematic diagram of capturing a screen touch area provided by an embodiment of the present application;
[0068] Fig.10 A schematic diagram of a coordinate system provided for an embodiment of the present application;
[0069] Fig.11 A schematic diagram of visual error distance calculation provided for one embodiment of the present application;
[0070] Fig.12 A schematic diagram of the structure of a touch screen visual error compensation device provided by one embodiment of the present application;
[0071] Fig.13 A schematic diagram of the structure of an electronic device provided in accordance with an embodiment of the present application. DETAILED DESCRIPTION
[0072] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.
[0073] The disclosure below provides many different embodiments or examples to realize the different structures of the present application. In order to simplify the disclosure of the present application, the parts and settings of specific examples are described below. Of course, they are only examples, and the purpose is not to limit the present application. In addition, the present application can repeat reference numbers and / or letters in different examples. This repetition is for the purpose of simplification and clarity, and does not itself indicate the relationship between the various embodiments and / or settings discussed.
[0074] In order to solve the technical problem in the prior art that the click intention of the target object and the actual response position of the touch screen are inconsistent, the present application provides a touch screen visual error compensation method, device, electronic device and storage medium, which can make the actual response position of the touch screen closer to the actual click intention of the target object, thereby improving the click accuracy of the user when using the touch screen.
[0075] The first embodiment of the present application provides a touch screen visual error compensation method, which can be applied to Figure 1 The system architecture shown in the figure includes at least a data acquisition module 101 and a data processing module 102, wherein the data acquisition module 101 and the data processing module 102 establish a communication connection, wherein the data acquisition module 101 can acquire the touch position of the target object touching the touch screen, and can also acquire the eye position of the target object and the position of the touching finger, etc. The data processing module 102 can calculate the first angle between the touching finger and the touch screen, the second angle between the eye of the target object and the touch screen, and the horizontal radius and vertical radius of the ellipse shape equivalent to the terminal knuckle of the touching finger according to the data acquired by the data acquisition module 101, and calculate the visual error distance according to the first angle, the second angle, the horizontal radius and the vertical radius, etc. The system architecture can be a terminal including a touch screen, such as a smart terminal, such as a tablet computer, a mobile phone and other devices, without limitation.
[0076] Next, based on the system architecture, the touch screen visual error compensation method is described in detail. Figure 2 , the touch screen visual error compensation method includes:
[0077] Step 201, obtaining terminal ellipse parameters of a touching finger of a target object; wherein the touching finger is a finger of the target object touching a touch screen, and the terminal ellipse parameters include a horizontal radius and a vertical radius of an ellipse shape equivalent to the terminal knuckle of the touching finger.
[0078] The target object refers to the user who manipulates the touch screen. Because the fingertips have an arc, when the user wants to click on point A on the screen, the user actually touches point B which is lower than point A. The above phenomenon is the manifestation of parallax error. Parallax error refers to the deviation in the observation of the position of an object due to the different positions of the observer's eyes. When using mobile phones and other devices, when we look at the screen from different angles, the position of the image seen by the eyes may be different from the actual touch position. This is the error caused by parallax. This error may make us think that we clicked on one position, but in fact the screen response is at another position, thus affecting the accuracy of the operation. It is mainly caused by the combined effect of human visual perception characteristics and the display characteristics of the device screen. Since few users' fingers are perpendicular to the screen to achieve click operations, parallax errors always exist in daily mobile phone operations.
[0079] In one embodiment, the system block diagram of the touch screen visual error compensation method can be as follows: Figure 3 , including screen touch system, facial recognition system, eye position detection system, observation angle analysis module, touch finger shape recognition management module, touch finger and screen angle recognition management module, parallax error compensation management module, etc.
[0080] Most users touch the screen with their index finger, which is more slender at the end. That is, the end of the actual observer's finger is closer to an ellipsoid than a sphere, and the ellipse in cross section is more oblate. In addition, the observer's line of sight is focused on the fingertip (which can be approximately equivalent to the left focus of the ellipse), not the center point of the ellipsoid corresponding to the fingertip. Figure 4 is a schematic diagram of the angle between the end of the finger and the screen. This angle can be called the first angle and is represented by α. Figure 5 : is a schematic diagram of the angle between the eye and the screen, which can be called the second angle, represented by β. When the viewing angle between the observer and the touch screen is the same, the angle between the finger and the touch screen is different, and the visual error is also different, that is, the smaller the first angle, the larger the visual error, and the larger the first angle, the smaller the visual error. Moreover, the visual deviation is not only in one direction, but also in both horizontal and vertical directions. In addition, the larger the second angle, the smaller the visual error, and the smaller the second angle, the larger the visual error. Therefore, both the first angle and the second angle will have a greater impact on the visual error.
[0081] In this embodiment, the terminal ellipse parameters include the horizontal radius and the vertical radius of the ellipse shape equivalent to the terminal knuckle of the touching finger, so that the equivalent ellipse shape is closer to the actual shape of the touching finger.
[0082] In one embodiment, obtaining the end ellipse parameters of the touching finger of the target object may include at least the following two methods:
[0083] The first method is to obtain the ellipse parameters of the end of the input touching finger. The value can be calculated from experience according to the thickness and curvature of the finger, and manually input through the control program.
[0084] The second method: obtain the finger image of the target object's touching finger captured by the camera; calculate the terminal ellipse parameters based on the finger image and the preset calculation model. The user's finger image can be captured by an external camera, and the vertical radius and horizontal radius can be calculated by an artificial intelligence algorithm. The external camera can be the camera built into the terminal device, such as the front camera of a mobile phone, without restriction.
[0085] Step 202: Obtain the relative position coordinates of the target object's eyes and touching finger.
[0086] In one embodiment, the relative position coordinates of the target object's eyes and the touching finger are obtained, including: determining a spatial coordinate system based on the camera of the terminal where the touch screen is located; obtaining the first spatial coordinates of the actual touch point in the spatial coordinate system; obtaining the second spatial coordinates of the target object's eyes in the spatial coordinate system captured by the camera; and determining the relative position coordinates based on the first spatial coordinates and the second spatial coordinates.
[0087] In this embodiment, the relative position diagram of the finger touch position and the eye position in the spatial coordinate system can be as follows: Figure 6 , the spatial coordinate system is determined based on the camera of the terminal where the touch screen is located. The position of the camera can be set as the coordinate origin of the spatial coordinate system. The first spatial coordinate of the actual touch point can be P (Xfinger, Yfinger, Zfinger), and the second spatial coordinate of the eye can be P (Xeye, Yeye, Zeye). Therefore, the relative position coordinates of the eye and the touching finger can be calculated based on P (Xfinger, Yfinger, Zfinger) and P (Xeye, Yeye, Zeye).
[0088] In one embodiment, obtaining the first spatial coordinate of the actual touch point in the spatial coordinate system includes: obtaining the actual touch point where the touching finger touches the touch screen; and determining the first spatial coordinate of the actual touch point in the spatial coordinate system based on the actual touch point, the screen resolution of the touch screen, and the screen size of the touch screen.
[0089] In this embodiment, first, when the finger touches the screen, the position coordinates of the actual touch point are identified. The system can recognize all touch screen events of the user, and the time point corresponding to the touch screen behavior event is determined based on the screen touch sampling rate of the current device. The time interval for each data sampling is consistent. Taking the screen touch sampling rate of 60Hz as an example, the time interval for recording the finger position each time is 1 / 60 second. When the finger touches the screen or moves, the system will capture the touch point position coordinates, recorded as P (Xscreen, Yscreen).
[0090] Secondly, convert the position coordinates of the actual touch point on the screen into Cartesian coordinates. Since the screen coordinate system returned by the system and the coordinate system of the mobile phone camera are different reference systems and measurement standards, it is necessary to convert the screen coordinates into Cartesian coordinates in order to unify the calculation caliber. The specific methods include:
[0091] Determine the resolution of your screen: Screen resolution refers to the number of pixels on the screen in the horizontal and vertical directions. For example, 1920x1080 means the screen has 1920 pixels horizontally and 1080 pixels vertically.
[0092] Determine the physical size of the screen: The physical size of a screen refers to the actual width and height of the screen, usually measured in inches.
[0093] Calculate the physical size of each pixel: By dividing the physical size of the screen by the resolution of the screen, you can get the physical size of each pixel. For example, if the physical size of the screen is 10 inches and the horizontal resolution is 1920 pixels, the physical size of each pixel is 10 inches / 1920 pixels.
[0094] Convert pixel coordinates to Cartesian coordinates: Pixel coordinates can be converted to Cartesian coordinates by multiplying the pixel coordinates by the physical size of each pixel. For example, for the pixel coordinates (x, y), multiply it by the physical size of each pixel, and the Cartesian coordinates are (x*physical size of each pixel, y*physical size of each pixel), recorded as P(Xtouch, Ytouch).
[0095] Finally, convert the two-dimensional screen coordinates into three-dimensional coordinates. Since the screen coordinates are two-dimensional and the eye coordinates captured by the camera are three-dimensional, the two-dimensional screen coordinates need to be converted into three-dimensional coordinates. The Z axis of the vertical screen is 0, so the first spatial coordinate of the actual touch point in the spatial coordinate system is P (Xtouch, Ytouch, 0).
[0096] In one embodiment, obtaining the second spatial coordinates of the target object's eyes in a spatial coordinate system captured by a camera includes: obtaining a head image of the target object captured by the camera; determining the left eye coordinates and the right eye coordinates of the target object in the spatial coordinate system based on the head image; and determining the second spatial coordinates of the target object's eyes in the spatial coordinate system based on the left eye coordinates and the right eye coordinates.
[0097] In this embodiment, the head image of the target object can be captured by a camera, the left eye coordinates and right eye coordinates of the target object in the spatial coordinate system can be determined based on the head image, the center point of the left eye coordinates and the right eye coordinates can be calculated, and the center point can be used as the second spatial coordinate of the target object's eye in the spatial coordinate system.
[0098] Step 203: Obtain a first angle between the touching finger and the touch screen.
[0099] In one embodiment, the first angle between the touching finger and the touch screen can be obtained in at least the following two ways:
[0100] The first method is to obtain an interactive image of the touching finger touching the touch screen, and determine the first angle according to the interactive image. For example, the interactive image of the end of the user's touching finger interacting with the screen can be collected by a camera, and the tilt angle between the end of the touching finger and the screen can be calculated by an artificial intelligence algorithm, and the tilt angle is the first angle.
[0101] The second method is to calculate the first angle by the contact area between the finger and the screen when the finger touches the screen, for example, when the finger touches the touch screen, the target contact area between the finger and the touch screen is obtained; the first angle is determined according to the target contact area and a preset mapping relationship. The mapping relationship is a mapping relationship between the contact area and the finger-screen angle; the target contact area is negatively correlated with the first angle.
[0102] Step 204: determine a second angle between the target object's eyes and the touch screen according to the relative position coordinates.
[0103] In one embodiment, determining the second angle between the target object's eye and the touch screen based on the relative position coordinates includes: determining the third angle between the target object's eye and the touch screen in a vertical axis direction based on the Y-axis coordinates of the relative position coordinates and the Z-axis coordinates of the relative position coordinates; determining the fourth angle between the target object's eye and the touch screen in a horizontal axis direction based on the X-axis coordinates of the relative position coordinates and the Z-axis coordinates of the relative position coordinates; and using the third angle and the fourth angle as the second angle between the target object's eye and the touch screen.
[0104] In this embodiment, the second angle may include a third angle between the target object's eye and the vertical axis direction of the touch screen, and a fourth angle between the target object's eye and the horizontal axis direction of the touch screen. The vertical axis deviation in the vertical axis direction may be calculated by the third angle, and the horizontal axis deviation in the horizontal axis direction may be calculated by the fourth angle, thereby further improving the accuracy of visual error compensation.
[0105] Step 205 , determining the visual error distance according to the first angle, the horizontal radius, the vertical radius, and the second angle.
[0106] In one embodiment, the visual error distance is determined based on a first angle, a horizontal radius, a vertical radius, and a second angle, including: determining a first distance between a focus of an equivalent elliptical shape and a center point of the equivalent elliptical shape based on the horizontal radius and the vertical radius; determining a vertical axis deviation based on the first distance, the first angle, and the third angle; determining a horizontal axis deviation based on the first distance, the first angle, and the fourth angle; and using the vertical axis deviation and the horizontal axis deviation as the visual error distance.
[0107] In this embodiment, the first distance is the distance between the focus and the center point of the equivalent elliptical shape. The vertical axis deviation can be determined by the first distance, the first angle and the third angle. The specific calculation method is described in detail in the following embodiment. The horizontal axis deviation is determined by the first distance, the first angle and the fourth angle.
[0108] In this embodiment, the first angle and the second angle are referred to, which can reduce the error caused by the difference between the first angle and the second angle. At the same time, the equivalent ellipsoid shape is combined to more accurately simulate the end knuckles of the actual touch screen, so that the actual response position of the touch screen is closer to the actual click intention of the target object, thereby improving the user's click accuracy when using the touch screen.
[0109] Step 206 , performing error compensation on the actual touch point of the touch screen touched by the touching finger according to the visual error distance.
[0110] The method converts the end knuckle of a touching finger into an elliptical shape, obtains a first angle between the touching finger and the touch screen, determines a second angle between the eyes of a target object and the touch screen, and determines a visual error distance according to the first angle, the second angle, and the horizontal radius and the vertical radius of the equivalent elliptical shape. According to the visual error distance, error compensation is performed on the actual touching point, thereby reducing the error caused by the first angle and the second angle. At the same time, the end knuckle of an actual touching touch screen is more accurately simulated by combining the equivalent ellipsoid shape, so that the actual response position of the touch screen is closer to the actual clicking intention of the target object, thereby improving the clicking accuracy of the user when using the touch screen.
[0111] In one embodiment, error compensation is performed on the actual touch point of the touching finger touching the touch screen according to the visual error distance, including: obtaining the vertical coordinate of the actual touch point and the horizontal coordinate of the actual touch point; compensating the vertical coordinate of the actual touch point according to the vertical axis deviation; and compensating the horizontal coordinate of the actual touch point according to the horizontal axis deviation.
[0112] In this embodiment, if the actual touch point coordinates are P (Xtouch, Ytouch), the vertical difference deviation is Dvertical, and the horizontal axis deviation is Dhorizontal, the compensated coordinates are P (Xresponse, Yresponse), where Xresponse = Xtouch + Dhorizontal, and Yresponse = Ytouch + Dvertical.
[0113] In a specific embodiment, when the user touches the screen, the angle relationship between the user (observer) and the screen is identified by taking the front camera of the mobile phone screen as a reference system and calculating the relative angle between the user's head and the screen. The specific implementation steps can be as follows:
[0114] 1. Mobile phone coordinate system selection
[0115] Taking the iOS system of iPhone as an example, the ARKit coordinate system in this system uses the Cartesian coordinate system to measure the real world. The device position when ARSession is turned on is the origin of the coordinate axis. The worldAlignment property of ARSessionConfiguration determines the direction of the three coordinate axes. This property has three enumeration values: ARWorldAlignmentCamera, ARWorldAlignmentGravity, and ARWorldAlignmentGravityAndHeading. Among them, ARWorldAlignmentCamera is the device posture that determines the direction of the three coordinate axes. This coordinate setting is suitable for coordinate calculations with the device as the reference system and has nothing to do with the real geographical environment. Therefore, it is more reasonable for the user to touch the mobile phone screen to refer to the mobile phone device as a reference system. The coordinate values of the user's eyes captured later in the embodiment of the present application are the coordinate system with the device as a reference.
[0116] 2. Eye Position Detection and Observation Angle Analysis
[0117] 1. Facial recognition system: Smartphone system facial recognition function
[0118] In current smart mobile phone systems, most device systems have built-in face detection and facial gesture recognition functions. Taking the iPhone as an example, face detection can be implemented in the iOS system through the basic library ARKit.
[0119] (1) ARKit Function
[0120] ARKit is integrated and expanded by integrating AVFoundation, CoreMotion, and CoreML frameworks. AVFoundation is a framework for processing time-based multimedia data, CoreMotion is a framework for processing sensor data information such as accelerometers, gyroscopes, and LiDAR, and CoreML is a machine learning framework. ARKit integrates video image information from AVFoundation and device motion sensor data from CoreMotion, and uses CoreML computer image processing and machine learning technology to provide developers with a stable three-dimensional digital environment.
[0121] ARKit uses the image information (including information collected by LiDAR) collected by the monocular camera of mobile devices (including mobile phones and tablets) to implement advanced functions such as plane detection and recognition, scene geometry, ambient light estimation, ambient light reflection, image recognition, 3D object recognition, face detection, and human motion capture. This article mainly uses plane detection and recognition and face detection. In addition, ARKit's sizing system is very stable and accurate. 1 unit in the ARKit scale space is equal to 1 meter in the real world.
[0122] (2) Tracking principle and face tracking
[0123] ARKit uses visual inertial odometry technology to perform computer vision analysis on the image sequence captured by the camera and combine it with the device's motion sensor information. ARKit identifies the feature points in each frame of the image, and based on the position changes of the feature points between consecutive image frames, it compares them with the information provided by the motion sensor to ultimately obtain high-precision device position and deflection information. Device tracking supports three attitude angles, Yaw, Pitch, and Roll, as well as offsets along the X, Y, and Z axes in the Cartesian coordinate system.
[0124] When ARKit detects a face, it adds an ARFaceAnchor to the scene, which can be used to implement positioning and tracking. If there are two faces, ARKit will only track the largest and most recognizable face. When the face is obtained, the X, Y, and Z coordinates of the left and right eyes can also be obtained.
[0125] 2. Eye position detection system
[0126] Take the iOS system of iPhone as an example. Based on the ARKit system function, create a session, configure input and output; set the callback proxy method. Specific steps: Create a running session (ARSession object). ARSession is responsible for managing the information of each frame, which mainly includes: taking images and obtaining sensor data, analyzing and processing the data, and then outputting them frame by frame. Configure the face tracking ARFaceTrackingConfiguration property, which mainly realizes the tracking of the position and direction of the face, including the eye coordinates. When the face in front of the camera changes, the proxy method will receive face-related information, such as the left eye coordinate value P (Xlefteye, Ylefteye, Zlefteye), and the right eye coordinate value P (Xrighteye, Yrighteye, Zrighteye).
[0127] 3. Observation angle analysis module: Use eye position coordinates to analyze the observer's angle.
[0128] The main purpose of the viewing angle analysis module is to calculate the viewing angle of the eye relative to the finger based on the finger touch position and the eye position. The specific algorithm includes:
[0129] (1) When a finger touches the screen, identify the touch screen position coordinates.
[0130] The system can recognize all touch screen events of the user. The time point corresponding to the touch screen behavior event is determined by the screen touch sampling rate of the current device. The time interval for each data sampling is consistent. Taking the screen touch sampling rate of 60Hz as an example, the time interval for each recording of the finger position is 1 / 60 second. When the finger touches the screen or moves, the system will capture the touch point position coordinates, recorded as P (Xscreen, Yscreen).
[0131] (2) Convert screen coordinates to Cartesian coordinates
[0132] Since the screen coordinate system returned by the system and the coordinate system of the mobile phone camera have different reference systems and measurement standards, the screen coordinates need to be converted into Cartesian coordinates in order to unify the calculation of the aperture. The specific methods include:
[0133] Determine the resolution of your screen: Screen resolution refers to the number of pixels on the screen in the horizontal and vertical directions. For example, 1920x1080 means the screen has 1920 pixels horizontally and 1080 pixels vertically.
[0134] Determine the physical size of the screen: The physical size of a screen refers to the actual width and height of the screen, usually measured in inches.
[0135] Calculate the physical size of each pixel: By dividing the physical size of the screen by the resolution of the screen, you can get the physical size of each pixel. For example, if the physical size of the screen is 10 inches and the resolution in the horizontal direction is 1920 pixels, the physical size of each pixel is 10 inches / 1920.
[0136] Convert pixel coordinates to Cartesian coordinates: Pixel coordinates can be converted to Cartesian coordinates by multiplying the pixel coordinates by the physical size of each pixel. For example, for the pixel coordinates (x, y), multiply it by the physical size of each pixel, and the Cartesian coordinates are (x*physical size of each pixel, y*physical size of each pixel), recorded as P(Xtouch, Ytouch).
[0137] (3) Convert the two-dimensional screen coordinates to three-dimensional coordinates
[0138] Since the screen coordinates are two-dimensional and the eye coordinates captured by the camera are three-dimensional, the two-dimensional screen coordinates need to be converted into three-dimensional coordinates. The Z axis vertical to the screen is 0, so the touch point coordinates are P (Xtouch, Ytouch, 0).
[0139] (4) Calculate the observer's eye coordinates
[0140] There is a coordinate difference between the left and right eyes of the observer, and the observer may have a tilted or deflected head. Therefore, the average value of the left and right eye coordinates is used as the observer coordinates, which is a relatively accurate coordinate value.
[0141] The calculation of P(Xeye, Yeye, Zeye) is:
[0142] Xeye=(Xlefteye+Xrighteye) / 2
[0143] Yeye=(Ylefteye+Yrighteye) / 2
[0144] Zeye=(Zlefteye+Zrighteye) / 2
[0145] (5) Calculate the relative position of the observer's eyes and the touching finger
[0146] The angle calculation method of the relative position P (Xsight, Ysight, Zsight) between the observer's eyes and the touching finger is:
[0147] Xsight=Xeye–Xtouch
[0148] Ysight=Yeye–Ytouch
[0149] Zsight=Zeye–0, that is (Zsight=Zeye)
[0150] 3. Finger shape recognition and touch screen angle estimation
[0151] 1. Touch finger shape recognition management module
[0152] (1) Identification of the optimal shape of the finger tip
[0153] In the industry's related methods for visual compensation of parallax errors in the screen touch dimension, the differences in the shape and size of the finger tips are rarely taken into account, and some solutions simply treat the user's finger tip as a sphere with a radius of r. First of all, in real life, since most people touch the screen with their index finger, and the tip of the index finger is more slender, the actual observer's finger tip is closer to an ellipsoid, and the elliptical shape of the cross-section is more oblate. Secondly, the position where the observer's line of sight focuses is the fingertip, not the center point of the ellipsoid corresponding to the fingertip. Therefore, there is a large deviation in the calculation of treating the fingertip as a sphere. In this embodiment, the finger tip is equivalent to an ellipsoid, and the cross-section is equivalent to an elliptical shape, which can improve the accuracy of the calculation process.
[0154] (2) Confirm the ellipsoid shape of the finger tip: vertical radius and horizontal radius
[0155] The fingertips of most users are roughly elliptical, such as Figure 7 , the vertical radius of the ellipse represents the thickness of the finger, and the horizontal radius of the ellipse represents the flatness of the finger. The sum of the distances between the moving point P and the two fixed points F1 and F2 in the plane is equal to the constant 2a, where 2a is greater than the distance between points F1 and F2, and the trajectory of the moving point P forms an ellipse. The two fixed points F1 and F2 are called the foci of the ellipse. The chord obtained by the ellipse intersecting the straight line coinciding with the line connecting the two foci is the major axis (horizontal radius), and the length of the major axis is 2a. The chord obtained by the ellipse intersecting the straight line perpendicularly bisecting the line connecting the two foci is the minor axis (vertical radius), and the length of the minor axis is 2b.
[0156] The ellipsoid shape at the end of the user's finger, that is, the thickness of the finger and the curvature of the finger, can be confirmed by confirming the vertical radius and horizontal radius of the ellipse of the finger section. The focus position of the ellipse can be inferred from the vertical radius and horizontal radius. The vertical radius and horizontal radius of the ellipse of the finger section can be confirmed in the following two ways: according to the different thickness and curvature of the finger, the value is inferred from the empirical value and manually input through the control program; or, the user's finger image is captured by an external camera, and the vertical radius and horizontal radius are calculated by the artificial intelligence algorithm.
[0157] 2. Touch finger and screen angle recognition management module
[0158] Within the limited range of the mobile phone screen, since the finger tip is in an arc shape, the parallax is different when it contacts the screen at different arc positions. Therefore, the angle between the distal phalanx contacting the screen and the screen will also affect the size of the user's observation error. The specific differences are as follows: Figure 8 , Figure 8 A schematic diagram of the visual error distance between a finger and a screen at different angles provided in an embodiment of the present application.
[0159] The method for identifying the angle between the end of a finger and the screen is as follows: using an external camera to capture the interaction image between the end of the user's finger and the screen, and using an artificial intelligence algorithm to calculate the inclination angle between the distal phalanx and the screen; or, calculating the angle based on the contact area between the finger and the screen when the finger touches the screen.
[0160] The system can recognize all the user's touch screen events. The time point corresponding to the touch screen behavior event is determined by the screen touch sampling rate of the current device. The time interval for each data sampling is consistent. Taking the screen touch sampling rate of 60Hz as an example, the time interval for each finger position recording is 1 / 60 second. When the finger touches the screen or moves, the system will capture the touch point position and the touch area of the finger and the screen. The schematic diagram of capturing the screen touch area is shown in the figure below. Fig. 9 The area of the screen touched by the finger will vary at different times. This may be due to a change in the finger's tilt angle or a change in the vertical radius of the finger's ellipse caused by a change in the pressing force.
[0161] By capturing a large number of touch events generated by a single user on the device (the contact area between the finger and the screen, the tilt angle between the finger and the screen corresponding to the area, the pressing force, and the vertical radius of the finger ellipse), and using artificial intelligence algorithms, we can identify the correlation between the user's commonly used contact area and tilt angle of daily touching the screen, and identify the relationship between the contact area and the vertical radius of the finger ellipse.
[0162] 4. Parallax Error Compensation Algorithm
[0163] Parallax error compensation management module: provides correction based on the observer's angle, finger characteristics and touch angle.
[0164] 1. Necessary data prerequisites:
[0165] The relative position P (Xsight, Ysight, Zsight) between the observer's eyes and the touching finger is calculated based on the finger touch position and the eye position through the "observation angle analysis module";
[0166] The ellipsoid shape of the finger end is confirmed through the "touch finger shape recognition management module": horizontal radius a, vertical radius b;
[0167] The angle α between the distal phalanx touching the screen and the screen is confirmed through the "touching finger and screen angle recognition management module".
[0168] 2. Parallax error compensation calculation:
[0169] A schematic diagram of a coordinate system is as follows Fig.10 , the visual error distance in the vertical and horizontal axes can be calculated respectively.
[0170] The schematic diagram of the visual error distance calculation of the vertical axis is as follows Fig.11 , the offset calculation method is as follows:
[0171] (1) Based on the horizontal radius a and the vertical radius b, calculate the distance F1O between the left focus F1 and the center point O (of course, F2O can also be calculated without restriction)
[0172] (2) Based on the angle α between the finger touching the screen and the screen (i.e., the first angle), it is deduced that:
[0173] From the sine function, we know that sinα=d2 / F1O, that is, d2=F1O*sinα;
[0174] From the tangent function, we know that tanα=d2 / (d1+d3), that is, d1+d3=d2 / tanα;
[0175] Among them, d1 and d3 constitute the first right-angled side of the right triangle, d2 constitutes the second right-angled side of the right triangle, F1O is the hypotenuse of the right triangle, therefore, α is the angle between the first right-angled side and the hypotenuse, that is, sinα=d2 / F1O, similarly, tanα=d2 / (d1+d3).
[0176] (3) According to the relative position P (Xsight, Ysight, Zsight) between the observer's eye and the touch screen, calculate the angle β (here β refers to the third angle in the vertical axis direction) between the observer's eye and the touch screen, tanβ = Zsight / Ysight. Tangent function tanβ = d2 / d3, that is, d3 = d2 / tanβ;
[0177] Among them, for the right triangle formed by d2, d3 and the hypotenuse (the line segment formed by the connecting point of d1 and d3 and F1), the angle between d3 and the hypotenuse is β, so tanβ=d2 / d3.
[0178] (4) According to d1+d3=d2 / tanα and d3=d2 / tanβ, it can be deduced that:
[0179] d1=(d2 / tanα)-(d2 / tanβ)
[0180] (5) Visual error distance d = d1 = (d2 / tanα) - (d2 / tanβ). Since d2 = F1O*sinα, F1O can be calculated based on the horizontal radius a and the vertical radius b. α and β are both known, so the specific value of d can be calculated.
[0181] Horizontal axis: The calculation method is the same as the calculation process for the vertical axis direction, with the difference that the angle β between the observer's eye and the touch screen is calculated as the fourth angle in the horizontal axis direction, tanβ=Zsight / Xsight.
[0182] 3. Provide parallax error compensation
[0183] Based on the vertical axis deviation Dvertical (i.e. d in the vertical axis direction) and horizontal axis deviation Dhorizontal (i.e. d in the horizontal axis direction) calculated in the previous step, the compensation coordinate algorithm after the user clicks the screen is given: the actual touch coordinate P (Xtouch, Ytouch) and the impact coordinate P (Xresponse, Yresponse), the calculation formulas for the two are as follows:
[0184] Xresponse=Xtouch+Dhorizontal
[0185] Yresponse=Ytouch+Dvertical
[0186] The impact coordinates are the coordinates of the touch screen response after compensation based on the actual touch coordinates.
[0187] In the embodiment of the present application, the horizontal radius a and the vertical radius b can characterize the physiological thickness characteristics of the user's fingers. The second angle can characterize the positional relationship between the user and the touch screen, such as sitting posture. The first angle can characterize the position of the finger when touching. Thus, according to the different physiological thickness characteristics of the fingers of different users and the different sitting positions of the users, a touch screen correction algorithm for compensating for parallax errors is provided, which can improve the accuracy of touch intention recognition of the touch screen.
[0188] Based on the same technical concept, the second embodiment of the present application provides a touch screen visual error compensation device, such as Fig.12 , the device comprises:
[0189] The first acquisition module 1201 is used to acquire terminal ellipse parameters of a touching finger of a target object; wherein the touching finger is a finger of the target object touching the touch screen, and the terminal ellipse parameters include a horizontal radius and a vertical radius of an ellipse shape equivalent to a terminal knuckle of the touching finger;
[0190] A second acquisition module 1202 is used to acquire the relative position coordinates of the target object's eyes and the touching finger;
[0191] A third acquisition module 1203 is used to acquire a first angle between the touching finger and the touch screen;
[0192] A first determining module 1204 is configured to determine a second angle between the eye of the target object and the touch screen according to the relative position coordinates;
[0193] A second determining module 1205 is used to determine a visual error distance according to the first angle, the horizontal radius, the vertical radius and the second angle;
[0194] The error compensation module 1206 is used to perform error compensation on the actual touch point of the touch screen touched by the touching finger according to the visual error distance.
[0195] The device converts the end knuckle of a touching finger into an elliptical shape, obtains a first angle between the touching finger and the touch screen, determines a second angle between the eyes of a target object and the touch screen, determines a visual error distance according to the first angle, the second angle, and the horizontal radius and the vertical radius of the equivalent elliptical shape, and performs error compensation on an actual touching point according to the visual error distance, thereby reducing the error caused by the first angle and the second angle. At the same time, the end knuckle of an actual touching touch screen is more accurately simulated by combining the equivalent ellipsoid shape, so that the actual response position of the touch screen is closer to the actual clicking intention of the target object, thereby improving the clicking accuracy of the user when using the touch screen.
[0196] like Fig.13 As shown, an embodiment of the present application provides an electronic device, including a processor 111, a communication interface 112, a memory 113 and a communication bus 114, wherein the processor 111, the communication interface 112, and the memory 113 communicate with each other through the communication bus 114.
[0197] Memory 113, used for storing computer programs;
[0198] In one embodiment of the present application, the processor 111 is used to execute the program stored in the memory 113 to implement the touch screen visual error compensation method provided by any of the above method embodiments, including:
[0199] Acquire the terminal ellipse parameters of the target object's touching finger; wherein the touching finger is the finger of the target object touching the touch screen, and the terminal ellipse parameters include the horizontal radius and the vertical radius of the ellipse shape equivalent to the terminal knuckle of the touching finger;
[0200] Acquire the relative position coordinates of the target object's eyes and the touching finger;
[0201] Acquire a first angle between the touching finger and the touch screen;
[0202] Determine a second angle between the eye of the target object and the touch screen according to the relative position coordinates;
[0203] Determine a visual error distance according to the first angle, the horizontal radius, the vertical radius and the second angle;
[0204] Error compensation is performed on an actual touch point of the touch screen touched by the touching finger according to the visual error distance.
[0205] The communication bus mentioned in the above terminal can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.
[0206] The communication interface is used for communication between the above terminal and other devices.
[0207] The memory may include a random access memory (RAM) or a non-volatile memory, such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.
[0208] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.
[0209] An embodiment of the present application further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the touch screen visual error compensation method provided by any of the aforementioned method embodiments is implemented.
[0210] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0211] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a general hardware platform, and of course, by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the relevant technology can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.
[0212] It should be understood that the terms used herein are only for the purpose of describing specific example embodiments and are not intended to be limiting. Unless the context clearly indicates otherwise, the singular forms "one", "an" and "said" as used herein may also be meant to include plural forms. The terms "include", "comprise", "contain", and "have" are inclusive, and therefore specify the existence of stated features, steps, operations, elements and / or parts, but do not exclude the existence or addition of one or more other features, steps, operations, elements, parts, and / or combinations thereof. The method steps, processes, and operations described herein are not interpreted as necessarily requiring them to be performed in the specific order described or illustrated, unless the execution order is clearly indicated. It should also be understood that additional or alternative steps may be used.
[0213] It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application. In the description, the suffixes such as "module", "component" or "unit" used to represent the elements are only used to facilitate the description of the present application and have no specific meaning in themselves. Therefore, "module", "component" or "unit" can be used in a mixed manner.
[0214] The above description is only a specific implementation of the present application, so that those skilled in the art can understand or implement the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest range consistent with the principles and novel features applied for herein.
Claims
1. A touch screen visual error compensation method, characterized in that: The method comprises: Acquire the terminal ellipse parameters of the target object's touching finger; wherein the touching finger is the finger of the target object touching the touch screen, and the terminal ellipse parameters include the horizontal radius and the vertical radius of the ellipse shape equivalent to the terminal knuckle of the touching finger; Acquire the relative position coordinates of the target object's eyes and the touching finger; Acquire a first angle between the touching finger and the touch screen; Determine a second angle between the eye of the target object and the touch screen according to the relative position coordinates; Determine a visual error distance according to the first angle, the horizontal radius, the vertical radius and the second angle; Error compensation is performed on an actual touch point of the touch screen touched by the touching finger according to the visual error distance.
2. The method according to claim 1, characterized in that: Get the end ellipse parameters of the target object's touching finger, including: Obtaining input terminal ellipse parameters of the touching finger; or, Acquire a finger image of the target object's touching finger captured by a camera; and calculate the terminal ellipse parameters according to the finger image and a preset calculation model.
3. The method according to claim 1, characterized in that: Acquiring the relative position coordinates of the target object's eyes and the touching finger, including: Determine a spatial coordinate system based on a camera of a terminal where the touch screen is located; Acquire the first spatial coordinate of the actual touch point in the spatial coordinate system; Acquire the second spatial coordinates of the eye of the target object captured by the camera in the spatial coordinate system; The relative position coordinates are determined according to the first space coordinates and the second space coordinates.
4. The method according to claim 1, characterized in that: Acquiring a first angle between the touching finger and the touch screen includes: Acquire an interactive image of the touch finger touching the touch screen; determine the first angle according to the interactive image; or, Obtain a target contact area between the touching finger and the touch screen when the touching finger touches the touch screen; determine the first angle according to the target contact area and a preset mapping relationship; wherein the mapping relationship is a mapping relationship between the contact area and the finger-screen angle; and the target contact area is negatively correlated with the first angle.
5. The method according to claim 1, characterized in that Determining a second angle between the eye of the target object and the touch screen according to the relative position coordinates includes: Determining a third angle between the eye of the target object and the vertical axis direction of the touch screen according to the Y-axis coordinate of the relative position coordinate and the Z-axis coordinate of the relative position coordinate; Determining a fourth angle between the eye of the target object and the horizontal axis direction of the touch screen according to the X-axis coordinate of the relative position coordinate and the Z-axis coordinate of the relative position coordinate; The third angle and the fourth angle are used as a second angle between the eye of the target object and the touch screen.
6. The method according to claim 5, characterized in that Determining a visual error distance according to the first angle, the horizontal radius, the vertical radius, and the second angle includes: Determine a first distance between the focus of the equivalent elliptical shape and the center point of the equivalent elliptical shape according to the horizontal radius and the vertical radius; determining a vertical axis deviation according to the first distance, the first angle, and the third angle; Determine a horizontal axis deviation according to the first distance, the first angle, and the fourth angle; The vertical axis deviation and the horizontal axis deviation are used as the visual error distance.
7. The method according to claim 6, characterized in that Performing error compensation on the actual touch point of the touch screen touched by the touch finger according to the visual error distance includes: Acquire the vertical coordinate of the actual touch point and the horizontal coordinate of the actual touch point; Compensating the vertical coordinate of the actual touch point according to the vertical axis deviation; The horizontal coordinate of the actual touch point is compensated according to the horizontal axis deviation.
8. The method according to claim 3, characterized in that Acquiring the second spatial coordinates of the eye of the target object captured by the camera in the spatial coordinate system includes: Acquire a head image of the target object captured by the camera; Determine the left eye coordinates and the right eye coordinates of the target object in the spatial coordinate system based on the head image; Determine the second spatial coordinates of the eye of the target object in the spatial coordinate system according to the left eye coordinates and the right eye coordinates.
9. The method according to claim 3, characterized in that: Acquiring the first spatial coordinate of the actual touch point in the spatial coordinate system includes: Acquire the actual touch point of the touch screen touched by the touching finger; The first spatial coordinate of the actual touch point in the spatial coordinate system is determined according to the actual touch point, the screen resolution of the touch screen, and the screen size of the touch screen.
10. A touch screen visual error compensation device, characterized in that: The device comprises: A first acquisition module is used to acquire terminal ellipse parameters of a touching finger of a target object; wherein the touching finger is a finger of the target object touching the touch screen, and the terminal ellipse parameters include a horizontal radius and a vertical radius of an ellipse shape equivalent to a terminal knuckle of the touching finger; A second acquisition module, used to acquire the relative position coordinates of the target object's eyes and the touching finger; A third acquisition module, used to acquire a first angle between the touching finger and the touch screen; A first determining module, configured to determine a second angle between the eye of the target object and the touch screen according to the relative position coordinates; A second determination module, configured to determine a visual error distance according to the first angle, the horizontal radius, the vertical radius and the second angle; The error compensation module is used to perform error compensation on the actual touch point of the touch screen touched by the touch finger according to the visual error distance.
11. An electronic device, characterized in that: It includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus; Memory, used to store computer programs; The processor is used to implement the touch screen visual error compensation method described in any one of claims 1 to 9 when executing the program stored in the memory.
12. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the touch screen visual error compensation method according to any one of claims 1 to 9 is implemented.
