A sight line recognition method, recognition device, terminal equipment and readable storage medium

Abstract

The present application is applicable to the field of vision detection technology, and provides a line of sight recognition method, recognition device, terminal equipment and readable storage medium, the method comprising: acquiring a first image, the first image comprising a preset reference object, the preset reference object being an item carried by a vision detection user; recognizing the shape of the preset reference object in the first image to obtain a first shape; if the first shape is different from the second shape, it is determined that the line of sight of the vision detection user is not perpendicular to the sight mark, and the second shape is the shape of the preset reference object when the line of sight of the vision detection user is perpendicular to the sight mark. The present application can solve the problem that current vision detection equipment cannot recognize whether the line of sight of the vision detection user is perpendicular to the sight mark.

Description

Technical Field

[0001] The present application relates to the field of vision detection, and in particular to a line of sight recognition method, a recognition device, a terminal device and a readable storage medium. Background Art

[0002] With the development of science and technology, electronic products are increasingly used in people's lives. However, long-term use of electronic products and unhealthy eye habits have led to an increasing number of people suffering from myopia. Therefore, it is necessary to regularly test vision to detect vision problems and correct them in time, thereby preventing myopia.

[0003] During vision testing, it is generally required that the sight line of the vision testing user is perpendicular to the sight mark, so that the test result is more accurate. However, in the actual test process, the vision testing user does not necessarily stand in front of the vision testing device. And the current vision testing equipment is generally fixed on the wall. Therefore, at this time, the sight line of the vision testing user is not perpendicular to the sight mark. When the sight line of the vision testing user is not perpendicular to the sight mark, the vision testing equipment cannot recognize it, resulting in inaccurate vision test results.

[0004] Therefore, the current vision testing equipment has the problem of being unable to identify whether the line of sight of the vision testing user is perpendicular to the sight mark. Summary of the invention

[0005] The embodiments of the present application provide a line of sight recognition method, a recognition device, a terminal device and a readable storage medium, which can solve the problem that current vision detection equipment cannot recognize whether the line of sight of a vision detection user is perpendicular to the visual mark.

[0006] In a first aspect, an embodiment of the present application provides a sight line recognition method, including:

[0007] Acquire a first image, wherein the first image includes a preset reference object, and the preset reference object is an item carried by a user for vision testing;

[0008] Recognizing the shape of the preset reference object in the first image to obtain a first shape;

[0009] If the first shape is different from the second shape, it is determined that the line of sight of the vision detection user is not perpendicular to the sight mark, and the second shape is the shape of the preset reference object when the line of sight of the vision detection user is perpendicular to the sight mark.

[0010] In a second aspect, an embodiment of the present application provides a sight line recognition device, including:

[0011] A first image acquisition module, used to acquire a first image, wherein the first image includes a preset reference object, and the preset reference object is an object carried by the vision detection user;

[0012] A recognition module, which recognizes the shape of the preset reference object in the first image to obtain a first shape;

[0013] A determination module is used to determine that the line of sight of the vision detection user is not perpendicular to the sight mark if the first shape is different from the second shape, and the second shape is the shape of the preset reference object when the line of sight of the vision detection user is perpendicular to the sight mark.

[0014] In a third aspect, an embodiment of the present application provides a terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method described in the first aspect when executing the computer program.

[0015] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method described in the first aspect are implemented.

[0016] In a fifth aspect, an embodiment of the present application provides a computer program product. When the computer program product is run on a terminal device, the terminal device executes the line of sight recognition method described in any one of the above-mentioned first aspects.

[0017] It can be understood that the beneficial effects of the second to fifth aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here.

[0018] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0019] As can be seen from the above, the present application provides a line of sight recognition method. First, a first image is obtained. The first image includes a preset reference object, and the preset reference object is an item carried by a vision detection user. Then, the shape of the preset reference object in the first image is identified to obtain a first shape. After obtaining the first shape, when the line of sight of the vision detection user is not perpendicular to the sight mark, the shape of the preset reference object carried by the vision detection user after imaging will change. For example, when the preset reference object is actually circular and the line of sight of the vision detection user is not perpendicular to the sight mark, the shape of the imaged reference object is elliptical. Therefore, if the first shape is different from the second shape, and the second shape is the shape of the preset reference object when the line of sight of the vision detection user is perpendicular to the sight mark, it can be determined that the line of sight of the vision detection user is not perpendicular to the sight mark. Therefore, in the present application, it can be determined whether the line of sight of the vision detection user is perpendicular to the sight mark by the preset reference object carried by the vision detection user. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0021] Figure 1 It is a flowchart of a sight line recognition method provided by an embodiment of the present application;

[0022] Figure 2 It is a top view of a preset reference object and a display screen displaying a sight mark provided by an embodiment of the present application;

[0023] Figure 3 is a front view of a preset reference object provided in an embodiment of the present application;

[0024] Figure 4 It is a schematic diagram of a three-dimensional sight mark before and after rotation provided by an embodiment of the present application.

[0025] Figure 5 It is a schematic diagram of the corresponding relationship between the test distance and the vision correction value provided in an embodiment of the present application;

[0026] Figure 6 is a schematic diagram of a method for determining the type of a test eye provided by an embodiment of the present application;

[0027] Figure 7 is a schematic diagram of a method for determining an eye occlusion state provided by an embodiment of the present application;

[0028] Figure 8 is a structural schematic diagram of a sight line recognition device provided by an embodiment of the present application;

[0029] Fig. 9 It is a schematic diagram of the structure of the terminal device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0030] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0031] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0032] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0033] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.

[0034] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0035] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0036] The line of sight recognition method provided in the embodiment of the present application can be applied to terminal devices such as mobile phones, tablet computers, laptop computers, ultra-mobile personal computers (UMPCs), netbooks, personal digital assistants (PDAs), etc. The embodiment of the present application does not impose any restrictions on the specific type of the terminal device.

[0037] In order to illustrate the technical solution described in this application, a specific embodiment is provided below for illustration.

[0038] Embodiment 1

[0039] The following is a description of a sight line recognition method provided in Example 1 of the present application. Figure 1 , the method comprising:

[0040] Step S101: Acquire a first image, where the first image includes a preset reference object, and the preset reference object is an item carried by a vision detection user.

[0041] In step S101, the first image refers to an image of the vision detection user before preparing for the vision detection or an image of the vision detection user during the vision detection. It should be understood that the first image can be an image captured by a camera when the terminal device performs a vision detection operation, or it can be an image captured when other terminal devices perform a vision detection operation and then sent to the terminal device. The user can select the source of the first image according to actual needs, and this application does not make specific restrictions on this.

[0042] The preset reference object can be a circular icon or a square icon, and the icon must have a certain pattern so that the icon can be recognized. The user can choose the preset reference object according to actual needs, and this application does not make specific restrictions here. When the vision testing user carries the preset reference object, the preset reference object can be attached to the eye mask, or it can be attached to the vision testing user and other things on the vision testing user. The user can choose the attachment place of the preset reference object according to actual needs, and this application does not make specific restrictions here.

[0043] Step S102: Identify the shape of a preset reference object in the first image to obtain a first shape.

[0044] In step S102, the method for identifying the shape of the preset reference object in the first image includes Fourier descriptor method, wavelet moment method and deep learning algorithm, etc. The user can select the method for identifying the shape of the preset reference object in the first image according to actual needs, and this application does not make any specific limitation here.

[0045] Step S103: If the first shape is different from the second shape, it is determined that the sight line of the vision testing user is not perpendicular to the sight mark, and the second shape is the shape of a preset reference object when the sight line of the vision testing user is perpendicular to the sight mark.

[0046] In step S103, since the shape of the preset reference object carried by the vision detection user after imaging will change when the sight line of the vision detection user is not perpendicular to the sight mark, the shape of the preset reference object when the sight line of the vision detection user is not perpendicular to the sight mark can be compared with the shape of the preset reference object when the sight line of the vision detection user is perpendicular to the sight mark. That is, the first shape is compared with the second shape. When the first shape is different from the second shape, it can be determined that the sight line of the vision detection user is not perpendicular to the sight mark.

[0047] In some embodiments, if the first shape is different from the second shape, it is determined that the line of sight of the vision detection user is not perpendicular to the sight mark, including: when the second shape is a circle, if the first shape is an ellipse, it is determined that the line of sight of the vision detection user is not perpendicular to the sight mark.

[0048] In this embodiment, the actual shape of the preset reference object is a circle, that is, the second shape is a circle. Therefore, when the sight line of the vision testing user is not perpendicular to the sight mark, the shape of the preset reference object after imaging is an ellipse. At this time, the first shape is an ellipse. Therefore, when the second shape is a circle, if the first shape is an ellipse, it is determined that the sight line of the vision testing user is not perpendicular to the sight mark.

[0049] In some embodiments, if the first shape is the same as the second shape, it is determined that the sight line of the vision detection user is perpendicular to the sight mark. In this embodiment, since the second shape is the shape of a preset reference object when the sight line of the vision detection user is perpendicular to the sight mark, when the first shape is the same as the second shape, the vision detection device can determine that the sight line of the vision detection user is perpendicular to the sight mark.

[0050] In some embodiments, after determining that the line of sight of the vision detection user is not perpendicular to the sight mark, it also includes: calculating the similarity between the first image and each preset image, the preset image is an image formed by rotating a pre-stored preset reference object in a first direction; determining the rotation direction corresponding to the preset image with the highest similarity as the first rotation direction; determining the first rotation angle according to the first shape, and performing an angle adjustment operation on the sight mark according to the first rotation angle and the first rotation direction, so that the sight mark is perpendicular to the line of sight of the vision detection user.

[0051] In this embodiment, the preset image is an image formed by rotating the pre-stored preset reference object in the first direction. That is, the preset reference object is first rotated in various directions and then imaged to obtain various preset images, and then each preset image is associated with the direction in which it is rotated. Therefore, after the first image is acquired, the similarity between the first image and each preset image is calculated, and the rotation direction corresponding to the preset image with the highest similarity is the rotation direction of the preset reference object, that is, the first rotation direction.

[0052] The method for calculating the similarity between the first image and each preset image can be selected or designed according to actual needs. For example, in this embodiment, a structural similarity measurement method, a cosine similarity method, and a histogram-based method are used as the method for calculating the similarity between the first image and each preset image. This application does not make specific limitations here.

[0053] Therefore, when the first shape is different from the second shape, the first rotation direction of the preset reference object is obtained and the first rotation angle is determined according to the first shape, and then the angle adjustment operation is performed on the sight mark according to the first rotation angle and the first rotation direction, so that the sight mark is perpendicular to the line of sight of the vision detection user.

[0054] In some possible implementations, when the first shape is an ellipse, determining a first rotation angle based on the first shape includes: obtaining a first length of the short axis and a second length of the long axis in the ellipse; and calculating an arccosine value based on the first length and the second length to obtain the first rotation angle.

[0055] In this implementation, according to Figure 2 as well as Figure 3 , a process of calculating the arc cosine value according to the first length and the second length to obtain the first rotation angle is described. Figure 2 201 is a top view of a preset reference object and a display screen displaying an optotype. 202 is a display screen displaying an optotype. The length of the actual diameter of the preset reference object is d. When the vision testing user stands at position 202, that is, when the preset reference object is located at position 202, the line of sight of the vision testing user is perpendicular to the optotype on the display screen 201 displaying the optotype. When the vision testing user moves to position 203, there is a horizontal offset angle ∠1 between the line of sight of the vision testing device and the optotype on the display screen 201 displaying the optotype, that is, the first rotation angle is ∠1.

[0056] According to the principle of geometry, ∠1=∠2=∠3=∠4=∠5=∠6. Among them, ∠6 represents the angle between the plane where the preset reference object is located and the plane where the display screen displaying the sight mark is located. Since the plane where the preset reference object at position 202 is located is parallel to the plane where the display screen displaying the sight mark is located, ∠6 also represents the angle between the plane where the preset reference object at position 203 is located and the plane where the preset reference object at position 202 is located. Figure 3 301 represents a front view of a preset reference object at position 203 (it should be understood that Figure 3 The preset reference object is only used as an example to illustrate the solution of the rotation angle. In fact, the preset reference object should have other patterns attached to it so that the preset reference object can be identified. 302 represents the front view of the preset reference object at position 202. At this time, the cosine value of ∠6 is the ratio of the projection length c of the actual radius 3013 on the plane where 302 is located to the length d / 2 of the actual radius 3013.

[0057] After the preset reference object at position 203 is imaged by the vision detection device, the actual diameter 204 of the preset reference object (the diameter where the actual radius 3013 is located) becomes 205. At this time, 205 is the minor axis of the ellipse, and the first length of the minor axis is 2c (the plane where the preset reference object at position 202 is located is parallel to the plane where the display screen displaying the sight mark is located, that is, the plane where 302 is located is parallel to the plane where the display screen displaying the sight mark is located. Therefore, the projection length of the actual radius 3013 on the plane where 302 is located is the same as the projection length on the plane where the vision detection device is located, both of which are c. The actual diameter 204 is the diameter where the actual radius 3013 is located. Therefore, the first length of the minor axis obtained after the actual diameter 204 is imaged is 2c). The actual diameter 3014 in the preset reference object obtains the major axis of the ellipse after the vision detection device is imaged. Since the actual diameter 3014 is perpendicular to the actual diameter 204 (the diameter where the actual radius 3013 is located) and parallel to the plane where the display screen displaying the sight mark is located, the length of the actual diameter 3014 after the vision detection device is imaged is still d. Therefore, the second length of the major axis of the ellipse is d. Therefore, the first length of the minor axis of the ellipse is 2c, and the second length of the major axis is d. Therefore, the arc cosine of the first length of the minor axis and the second length of the major axis can be calculated to obtain the size of ∠6, that is,

[0058] ∠6=arccos(2c / d)

[0059] And ∠6=∠1, therefore, the size of the first rotation angle ∠1 can be obtained.

[0060] After the magnitude of the first rotation angle ∠1 is obtained, an angle adjustment operation is performed on the sight mark according to the first rotation angle and the first rotation direction.

[0061] In some other possible implementations, performing an angle adjustment operation on the sight mark according to the first rotation angle and the first rotation direction includes: controlling a display screen for displaying the sight mark to rotate the first rotation angle in the first rotation direction. In this embodiment, the vision detection device controls the display screen for displaying the sight mark to rotate the first rotation angle in the first rotation direction, so that the sight mark is perpendicular to the line of sight of the vision detection user, thereby making the subsequent vision detection result more accurate.

[0062] In some other possible implementations, the sight mark is a three-dimensional sight mark, and accordingly, according to the first rotation angle and the first rotation direction, an angle adjustment operation is performed on the sight mark, including: controlling the three-dimensional sight mark to rotate by the first rotation angle in the first rotation direction. In this implementation, since the sight mark is a three-dimensional sight mark, the vision detection device does not need to control the display screen displaying the sight mark to rotate by the first rotation angle in the first rotation direction, but directly controls the three-dimensional sight mark to rotate by the first rotation angle in the first rotation direction. Figure 4As shown, 401 represents the sight mark displayed before the rotation, and 402 represents the sight mark displayed after the rotation. In this embodiment, by controlling the three-dimensional sight mark to rotate in the first rotation direction by the first rotation angle, it is not necessary to control the display screen displaying the sight mark to rotate in the first rotation direction by the first rotation angle, which is more convenient while making the sight mark perpendicular to the line of sight of the vision test user.

[0063] In other embodiments, after determining that the line of sight of the vision detection user is not perpendicular to the sight mark, it also includes: performing a prompt operation to prompt the vision detection user to stand in the vision detection area. In this embodiment, when the line of sight of the vision detection user is not perpendicular to the sight mark, the vision detection device performs a prompt operation to prompt the vision detection user to stand in the vision detection area, so that the line of sight of the vision detection user is perpendicular to the sight mark. The prompt method includes but is not limited to voice prompts, displaying prompt information on the display screen, etc. The user can choose the prompt method according to actual needs, and this application does not make specific limitations here.

[0064] In summary, the present application provides a line of sight recognition method. First, a first image is acquired. The first image includes a preset reference object, and the preset reference object is an item carried by a vision detection user. Then, the shape of the preset reference object in the first image is identified to obtain a first shape. After obtaining the first shape, when the line of sight of the vision detection user is not perpendicular to the sight mark, the shape of the preset reference object carried by the vision detection user after imaging will change. For example, when the preset reference object is actually circular and the line of sight of the vision detection user is not perpendicular to the sight mark, the shape of the imaged reference object is elliptical. Therefore, if the first shape is different from the second shape, and the second shape is the shape of the preset reference object when the line of sight of the vision detection user is perpendicular to the sight mark, it can be determined that the line of sight of the vision detection user is not perpendicular to the sight mark. Therefore, in the present application, it can be determined whether the line of sight of the vision detection user is perpendicular to the sight mark by the preset reference object carried by the vision detection user.

[0065] In some embodiments, after the vision testing user's line of sight is perpendicular to the sight mark, the vision testing device obtains the sight mark feedback information, and determines the target vision testing value based on the sight mark feedback information and the information of the sight mark, wherein the sight mark feedback information is used to represent the recognition result of the vision testing user based on the opening direction feedback of the sight mark, and the information of the sight mark includes the opening direction information corresponding to the sight mark and the vision value information corresponding to the sight mark.

[0066] In this embodiment, after the sight line of the vision detection user is perpendicular to the sight mark, the vision detection user starts the vision detection. The vision detection user identifies the opening direction of the displayed sight mark and feeds back the recognition result of the opening direction of the sight mark by the vision detection user to the vision detection device through the first preset method. After receiving the recognition result of the opening direction of the sight mark by the vision detection user, the vision detection device obtains the sight mark feedback information according to the recognition result of the opening direction of the sight mark by the vision detection user, and then judges whether the recognition of the displayed sight mark by the vision detection user is correct according to the opening direction information of the displayed sight mark. For example, if the displayed sight mark is facing upward, it is judged whether the judgment result of the displayed sight mark in the sight mark feedback information is also facing upward. If the judgment result of the displayed sight mark in the sight mark feedback information is also facing upward, it is judged that the judgment of the displayed sight mark by the vision detection user is correct, so as to judge that the vision detection user can see the displayed sight mark clearly. If the vision detection user can see the displayed sight mark clearly, the vision detection device displays the sight mark of the previous level. For example, if the vision value corresponding to the displayed sight mark that the vision detection user can see clearly is 4.9, then the sight mark corresponding to the vision value 5.0 is displayed.

[0067] It should be noted that in order to more accurately determine whether the vision test user can see the visual mark of this level, the vision test user can judge multiple visual marks of the same level, and accumulate the number of correct judgments. If the number of correct judgments is equal to the first threshold, it is determined that the vision test user can see the visual mark of this level. In addition, in order to obtain the vision test result more accurately, it is set that the target vision test value is output only when the number of correct judgments of the visual mark of this level by the vision test user is equal to the first threshold, and the number of wrong judgments of the visual mark of the previous level of this level is equal to the second threshold. For example, when the number of times the vision test user correctly judges the visual mark corresponding to the visual acuity of 4.8 is equal to 4, and the number of wrong judgments of the visual mark corresponding to the visual acuity of 4.9 is equal to 3, the test result of the visual acuity of 4.8 is output. It should be understood that the first threshold and the second threshold can be a fixed value or a numerical range. The user can set it according to actual needs, and this application does not make specific restrictions here.

[0068] In some possible implementations, the vision detection user feeding back the vision detection user's recognition result of the opening direction of the sight mark to the vision detection device in a first preset manner may include: the vision detection user sending the vision detection user's recognition result of the opening direction of the sight mark to the vision detection device through an eye mask. For example, four buttons of "up", "down", "left" and "right" are set on the eye mask. When the opening direction of the displayed sight mark is upward, the vision detection user sends the vision detection user's recognition result of the opening direction of the sight mark to the terminal device by clicking the "up" button. When the opening direction of the displayed sight mark is to the left, the vision detection user sends the vision detection user's recognition result of the opening direction of the sight mark to the terminal device by clicking the "left" button.

[0069] In some other possible implementations, the vision detection user feeds back the vision detection user's recognition result of the opening direction of the sight mark to the vision detection device through a first preset method, which may include: the vision detection user sends the vision detection user's recognition result of the opening direction of the sight mark to the vision detection device through the direction of the vision detection user's finger. Then the vision detection device obtains the image of the vision detection user's finger, and then obtains the sight mark feedback information based on the image of the vision detection user's finger. During the detection process, the vision detection user uses his finger to indicate the opening direction of the sight mark, and the vision detection device obtains the finger image through a camera and identifies it, obtains the direction indicated by the finger, and thus obtains the sight mark feedback information. The method for obtaining the recognition result of the opening direction of the sight mark by the vision detection user can be set according to actual needs, and this application does not make specific limitations here.

[0070] It should be noted that the number of sight marks displayed each time is 1, and if no sight mark feedback information is obtained within a preset time, the next sight mark is switched, and if the number of sight marks for which no sight mark feedback information is obtained continuously reaches a preset threshold, the detection is stopped.

[0071] In some embodiments, before starting the vision test, it is also possible to obtain the target identity information of the vision test user, obtain the historical vision test values ​​corresponding to the target identity information, determine the first level of the displayed visual mark based on the historical vision test values, and adjust the level of the displayed visual mark to the first level.

[0072] In this embodiment, the target identity information can be obtained by performing face recognition on the face image collected by the camera, or by collecting the fingerprint information of the vision detection user, or by collecting the identity card information of the vision detection user. It should be understood that if the vision detection user is a student, the target identity information can also be obtained by collecting campus card information. In this application, the method for obtaining the target identity information can be selected according to the actual situation, and this application is not specifically limited here.

[0073] It should be noted that when obtaining the target identity information by performing face recognition on the images collected by the camera, if multiple faces are recognized, the non-detected users are prompted to leave the shooting range. At the same time, the vision detection device can periodically collect images through the camera and perform face recognition on the periodically collected images. When only one face is recognized, the historical vision detection value corresponding to the target identity information is obtained.

[0074] After the target identity information is obtained, the historical vision test value corresponding to the target identity information is obtained. Obtaining the historical vision test value corresponding to the target identity information includes: matching the target identity information with the identity information in a preset identity information database; if the preset identity information database contains identity information matching the target identity information, then obtaining the historical vision test value corresponding to the target identity information.

[0075] In this embodiment, the identity of the user undergoing vision testing can be authenticated, that is, the target identity information is matched with the identity information in the preset identity information database, and if there is identity information matching the target identity information in the preset identity information database, the verification is passed, and then the historical vision test value corresponding to the target identity information is obtained.

[0076] It should be understood that the identity information in the preset identity information database can be generated after the user registers, or can be generated after the school administrator uniformly inputs the identity information of the students. The generation method of the identity information in the preset identity information database can be set according to the actual situation, and this application does not make specific limitations here.

[0077] In some other embodiments, if an eyeblind is provided on a vision testing device, when the vision testing user takes the eyeblind from the vision testing device, the identity of the vision testing user also needs to be verified. If the identity verification is passed, the vision testing user can take out the eyeblind. After the vision testing user takes out the eyeblind, when the target identity information is obtained according to a preset method, the identity verification of the vision testing user can be performed again to confirm the identity of the vision testing user, to prevent the identity of the user who takes out the eyeblind from being inconsistent with the identity of the vision testing user. It should be noted that the identity verification methods before and after can be the same or different. The user can make a choice according to the actual situation, and this application does not make any specific limitation here.

[0078] After the historical vision test values ​​are obtained, the first level of the displayed visual mark is determined according to the historical vision test values ​​and the level of the displayed visual mark is adjusted to the first level.

[0079] The sight mark refers to a preset detection pattern. The specific shape of the sight mark can be set according to the actual situation. For example, the sight mark can be the letter E on the international standard vision chart, or the sight mark can also be a C-shaped ring on the blue ring vision chart. After obtaining the target identity information, the historical vision test value corresponding to the target identity information is obtained, and then the level of the sight mark displayed for the first time is determined according to the historical vision test value and the sight mark corresponding to the level is displayed.

[0080] In other embodiments, if the target identity information does not have a corresponding historical vision test value, the level of the visual mark displayed for the first time is determined according to a preset level and the visual mark corresponding to the level is displayed.

[0081] In other embodiments, before starting the vision test, the vision test device may perform an eye-covering prompt operation to prompt the vision test user to cover his eyes. In some possible implementations, the eye-covering prompt operation includes prompting the vision test user to cover his left eye or right eye. In other possible implementations, the eye-covering prompt operation may simply prompt the vision test user to cover his eyes.

[0082] In other embodiments, after determining the target vision test value based on the sight mark feedback information and the sight mark information, it includes: obtaining the most recent vision test value corresponding to the target identity information; calculating the deviation value between the target vision test value and the most recent vision test value; if the deviation value is greater than or equal to the preset deviation threshold, performing a re-test prompt operation.

[0083] In this embodiment, the deviation value of the target vision detection value and the most recent vision detection value corresponding to the target identity information is calculated. If the deviation value is greater than or equal to the preset deviation threshold, it means that the vision of the user performing the vision detection has been greatly reduced, and there may be an error in the vision detection. Therefore, the vision detection device performs a re-detection prompt operation to prompt the vision detection user to re-perform the vision detection. Alternatively, when the vision detection value of the left eye this time is the vision detection value of the right eye last time, and the vision detection value of the right eye this time is the vision detection value of the left eye last time, it means that there may be an error in the vision detection at this time. Therefore, at this time, the vision detection device may also perform a re-detection prompt operation to prompt the user to re-perform the vision detection. It should be noted that the above-listed conditions for triggering the execution of the re-detection prompt operation are only an example. When other abnormal situations occur, the re-detection prompt operation may also be triggered.

[0084] In some other examples, after obtaining the target vision test value, the target vision test value can be directly displayed, or the target vision test value can be sent to a server for storage, so that subsequent analysis and suggestions can be made based on the test data of the vision test user. It should be noted that if the user performing the vision test is a student, the target vision test value can also be sent to the parents so that the parents can understand the student's vision condition in real time.

[0085] In other embodiments, the technical solution of the present application also includes: identifying the test distance of the vision testing user, and determining the vision correction value based on the test distance, the test distance refers to the distance between the vision testing user and the sight mark during the vision test; accordingly, based on the sight mark feedback information and the information of the sight mark, determining the target vision testing value, including: determining a preliminary vision testing value based on the sight mark feedback information and the information of the sight mark; adding the preliminary vision testing value to the vision correction value to obtain the target vision testing value.

[0086] In vision testing, vision testing users are generally required to stand in a standard position for testing. For example, the standard international vision chart requires that the distance between the vision testing user and the sight mark is 5 meters. However, in actual testing, it is difficult for vision testing users to stand exactly 5 meters away from the sight mark. If they do not stand 5 meters away from the final sight mark, errors will occur in the vision test value. Therefore, before determining the target vision test value, the present application identifies the test distance of the vision test user, determines the vision correction value based on the test distance, and then determines the preliminary vision test value based on the sight mark feedback information and the information of the sight mark, and finally adds the preliminary vision test value to the vision correction value to obtain the target vision test value, so that the final target vision test value is more accurate. In some embodiments, the correction value can be calculated according to the following formula:

[0087]

[0088] Wherein, e is the correction value, L is the test distance of the vision test user, and m is the standard distance. It should be understood that the accuracy of the vision correction value can be set according to actual conditions. For example, the accuracy of the vision correction value can be set to 0.1.

[0089] You can refer to Figure 5 , Figure 5 shows some examples of vision correction values ​​for the test distances. Figure 5 The unit of the test distance is: meter. Assuming that the standard distance is 5 meters, and the above vision correction value calculation formula is used to calculate the vision correction value, when the test distance is 1 meter, the vision correction value is -0.7; when the test distance is 1.2 meters, the vision correction value is -0.6; when the test distance is 1.5 meters, the vision correction value is -0.5; when the test distance is 2 meters, the vision correction value is -0.4; when the test distance is 2.5 meters, the vision correction value is -0.3; when the test distance is 3 meters, the vision correction value is -0.2; when the test distance is 4 meters, the vision correction value is -0.1; when the test distance is 5 meters, the vision correction value is 0; when the test distance is 6.3 meters, the vision correction value is 0.1; when the test distance is 8 meters, the vision correction value is 0.2; when the test distance is 10 meters, it is 0.3.

[0090] In some possible implementations, the test distance of the vision test user can be identified by:

[0091] L=Df / d

[0092] Among them, L is the test distance of the vision detection user, f is the focal length of the camera, D is the actual diameter of the reference object, and d is the calculated length of the first reference object.

[0093] In this implementation, the first reference object is a circular icon, and the circular icon must have a certain pattern so that the circular icon can be identified. It should be noted that the first reference object may be the same as the preset reference object, or may be different from the preset reference object. The user can make a selection based on actual needs, and this application does not make any specific limitations here. During the vision test, the circular icon can be attached to the eye mask, or it can be attached to the user and other things on the user. The user can choose the attachment location of the first reference object based on actual needs, and this application does not make any specific limitations here.

[0094] Next, the calculation process of the length of the first reference object is described.

[0095] First, obtain the first reference object image, identify the first reference object image, and obtain the outer contour points of the first reference object. Since the first reference object is a circular icon, the shape composed of the outer contour points of the first reference object is a circle or an ellipse. When the shape composed of the outer contour points is a circle, calculate the length of any first line segment, which passes through the center of the circle and both endpoints of the first line segment are the outer contour points. At this time, the length of the first line segment is the calculated length of the first reference object. When the shape composed of the outer contour points is an ellipse, calculate the distance between the two endpoints on the major axis of the ellipse. At this time, the distance is the calculated length of the first reference object.

[0096] The length of the first line segment or the distance between the two endpoints on the major axis of the ellipse can be calculated based on the position coordinates of the outer contour points, or based on the number of pixels between any two contour points on the outer contour of the circle (the number of pixels between the two endpoints on the major axis of the ellipse), the camera pixels, and the width (or height) of the photosensitive chip. In this case, the length calculation formula of the first reference object is as follows:

[0097] d=ws / a

[0098] or,

[0099] d = hs / b

[0100] It should be noted that if the preliminary vision test value is added to the vision correction value to obtain the target vision test value, then when determining the level of the visual acuity mark to be displayed based on the historical vision test value, it is necessary to first subtract the correction value corresponding to the historical vision test value from the historical vision test value, and then obtain the first vision test value, and then obtain the level of the visual acuity mark to be displayed for the first time based on the first vision test value.

[0101] In other embodiments, the technical solution of the present application also includes: obtaining a first facial image captured by a camera, the first facial image is a facial image of a vision testing user undergoing a vision test; extracting first facial feature points on the first facial image, obtaining position information of each first facial feature point, and determining a target type of the test eye of the vision testing user according to the position information of the first facial feature points, the target type including one of the left or right side, and accordingly, determining a target vision detection value based on the sight mark feedback information and the information of the sight mark, including: determining a target vision detection value of a target eye of the vision testing user based on the sight mark feedback information and the information of the sight mark, the target eye being an eye of the target type.

[0102] In this embodiment, the extracted first facial feature points include: eye feature points 601, nose tip feature points 602, and mouth corner feature points 603. Before determining the vision test result, this embodiment first determines the target type of the test eye, so as to determine whether the test data is for the left eye or the right eye. The target type of the test eye is determined based on the position information of the first facial feature point, and the specific process is as follows:

[0103] like Figure 6 The coordinate axis is established with the preset point in the lower left corner of the first face image as the coordinate origin to obtain the position information of each first face feature point. For example, the coordinates of the eye feature point 601 are (x1, y1), the coordinates of the nose tip feature point 602 are (x2, y2), and the coordinates of the mouth corner feature point 603 are (x3, y3) and (x4, y4).

[0104] After obtaining the position information of each feature point, a straight line is drawn through the corner of mouth feature point 603, and then a perpendicular line x=x2 is drawn through the nose tip feature point 602 to extend the perpendicular line. After obtaining the perpendicular line, the abscissa x2 of the perpendicular line is compared with the abscissa x1 of the eye feature point 601. If the abscissa x1 of the eye feature point is less than the abscissa x2 of the perpendicular line, the target type of the tested eye is determined to be the right side. If the abscissa x1 of the eye feature point is greater than the abscissa x2 of the perpendicular line, the target type of the tested eye is determined to be the left side. Alternatively, after obtaining the perpendicular line, the perpendicular line is used as the axis of symmetry to solve the symmetric point 604 of the eye feature point 601 about the axis of symmetry, and the coordinates of the symmetric point 604 are (x5, y5). After obtaining the symmetric point 604, the abscissa x1 of the eye feature point is compared with the abscissa x5 of the symmetric point. If x1 is less than x5, the target type of the tested eye is determined to be the right side, and if x1 is greater than x5, the target type of the tested eye is determined to be the left side.

[0105] In this embodiment, if the eye covering prompt operation includes prompting the vision testing user to cover the left eye or the right eye, the vision testing device will verify again whether the tested eye is the left eye or the right eye, in case the vision testing user does not operate according to the prompt, so that it can more accurately determine whether the tested data belongs to the right eye or the left eye. Or the eye covering prompt operation only includes prompting the vision testing user to cover the eyes. At this time, the vision testing user can choose to test the left eye or the right eye first according to his own needs, and then the vision testing device will determine whether the tested eye is the left eye or the right eye, so that the user can choose whether to test the left eye or the right eye first according to his own needs.

[0106] In another embodiment, the technical solution of the present application also includes: obtaining a second facial image captured by a camera, the second facial image is a facial image of a vision detection user holding an eye mask for vision detection, the eye mask is used for the vision detection user to cover the eyes during the vision detection, identifying the eye mask on the second facial image, determining the center position information of the eye mask, extracting second facial feature points on the second facial image, obtaining the position information of each second facial feature point, determining the occlusion state of the eyes according to the position information of the second facial feature points and the center position information of the eye mask, the occlusion state including a correct occlusion state and an incorrect occlusion state; if the occlusion state is an incorrect occlusion state, performing a re-occlusion prompt operation.

[0107] In this embodiment, the second facial feature points may include: eye feature points 701, nose tip feature points 702, and mouth corner feature points 703. It should be noted that: Figure 7 705 in the figure is an eye shield.

[0108] The occlusion state of the eyes is monitored to determine whether the eyes of the vision test user are correctly occluded during the vision test. If the occlusion is incorrect, the vision test can be paused and the user can be reminded to occlude again until the user occludes correctly and then the vision test can be started again. In some embodiments, if the eyes of the vision test user are incorrectly occluded during the vision test, the data obtained when the occlusion is incorrect can also be marked, and then these data can be removed when determining the vision test result.

[0109] The calculation process of determining the occlusion state of the eyes according to the position information of the second facial feature points and the center position information of the eye mask includes: first, establishing a coordinate axis with the lower left corner preset point in the second facial image as the coordinate origin to obtain the position information of each second facial feature point. For example, the coordinates of the eye feature point 701 are (x6, y6), the coordinates of the nose tip feature point 702 are (x7, y7), the coordinates of the mouth corner feature point 703 are (x8, y8), (x9, y9), and the coordinates of the center point 7051 of the eye mask are (x 10 ,y 10 ).

[0110] After obtaining the position information of each second facial feature point, connect the mouth corner feature points into a straight line, then draw a perpendicular line through the nose tip feature point and extend the perpendicular line. After obtaining the perpendicular line, use the perpendicular line as the symmetry axis to solve the symmetric point 704 of the eye feature point 701 about the symmetry axis, and the coordinates of the symmetric point 704 are (x 11 ,y 11 ). Then the Euclidean distance between the symmetrical point 704 and the center point 7051 of the eye mask is calculated. If the Euclidean distance is less than a preset threshold, it is determined that the occlusion is correct. If the Euclidean distance is greater than the preset threshold, it is determined that the occlusion is incorrect.

[0111] In this embodiment, it is monitored whether the user's eyes are covered correctly during the vision test. If the covering is incorrect, the vision test can be paused and the user can be reminded to cover the eyes again until the user covers the eyes correctly. The vision test can then be started again, thereby more accurately judging the user's vision test results.

[0112] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0113] Embodiment 2

[0114] Figure 8 An example of a sight line recognition device is shown. For ease of explanation, only the parts related to the embodiment of the present application are shown. The device 800 includes:

[0115] The first image acquisition module 801 is used to acquire a first image, where the first image includes a preset reference object, and the preset reference object is an item carried by a vision detection user.

[0116] The recognition module 802 recognizes the shape of the preset reference object in the first image to obtain a first shape.

[0117] The determination module 803 is used to determine that the sight line of the vision detection user is not perpendicular to the sight mark if the first shape is different from the second shape, and the second shape is the shape of the preset reference object when the sight line of the vision detection user is perpendicular to the sight mark.

[0118] Optionally, the determination module 803 is used to execute:

[0119] When the second shape is a circle, if the first shape is an ellipse, it is determined that the sight line of the vision testing user is not perpendicular to the sight mark.

[0120] Optionally, the device 800 further includes:

[0121] The calculation module is used to calculate the similarity between the first image and each preset image, where the preset image is an image formed by rotating a pre-stored preset reference object in a first direction.

[0122] The rotation direction determining module is used to determine the rotation direction corresponding to the preset image with the highest similarity as the first rotation direction.

[0123] The rotation angle determination module is used to determine a first rotation angle according to the first shape.

[0124] The angle adjustment module is used to perform an angle adjustment operation on the sight mark according to the first rotation angle and the first rotation direction, so that the sight mark is perpendicular to the line of sight of the vision detection user.

[0125] Optionally, when the first shape is an ellipse, the rotation angle determination module includes:

[0126] The acquisition unit is used to acquire a first length of a minor axis and a second length of a major axis in the ellipse.

[0127] The calculation unit is used to calculate the arc cosine value according to the first length and the second length to obtain the first rotation angle.

[0128] Optionally, the angle adjustment module is used to perform:

[0129] A display screen for displaying a sight mark is controlled to rotate in a first rotation direction by a first rotation angle.

[0130] Optionally, the sight mark is a three-dimensional sight mark.

[0131] Accordingly, the angle adjustment module is used to perform:

[0132] The three-dimensional sight mark is controlled to rotate in a first rotation direction and at a first rotation angle.

[0133] Optionally, the apparatus 800 further includes:

[0134] The prompt module is used to perform a prompt operation to prompt the vision detection user to stand in the vision detection area.

[0135] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / units are based on the same concept as the first embodiment of the method of the present application. Their specific functions and technical effects can be found in the part of the method embodiment and will not be repeated here.

[0136] Embodiment 3

[0137] Fig. 9 Schematic diagram of the terminal device provided in the third embodiment of the present application. Fig. 9As shown, the terminal device 900 of this embodiment includes: a processor 901, a memory 902, and a computer program 903 stored in the memory 902 and executable on the processor 901. When the processor 901 executes the computer program 903, the steps in the above-mentioned method embodiments are implemented. Alternatively, when the processor 901 executes the computer program 903, the functions of the modules / units in the above-mentioned device embodiments are implemented.

[0138] Exemplarily, the computer program 903 may be divided into one or more modules / units, which are stored in the memory 902 and executed by the processor 901 to complete the present application. The one or more modules / units may be a series of computer program instruction segments capable of completing specific functions, which are used to describe the execution process of the computer program 903 in the terminal device 900. For example, the computer program 903 may be divided into a first image acquisition module, a recognition module, and a determination module, and the specific functions of each module are as follows:

[0139] Acquire a first image, wherein the first image includes a preset reference object, and the preset reference object is an item carried by a vision detection user;

[0140] Recognizing the shape of the preset reference object in the first image to obtain a first shape;

[0141] If the first shape is different from the second shape, it is determined that the line of sight of the vision detection user is not perpendicular to the sight mark, and the second shape is the shape of the preset reference object when the line of sight of the vision detection user is perpendicular to the sight mark.

[0142] The terminal device may include, but is not limited to, a processor 901 and a memory 902. Those skilled in the art will appreciate that Fig. 9 It is only an example of the terminal device 900 and does not constitute a limitation of the terminal device 900. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the terminal device may also include input and output devices, network access devices, buses, etc.

[0143] The processor 901 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware plug-ins, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0144] The memory 902 may be an internal storage unit of the terminal device 900, such as a hard disk or memory of the terminal device 900. The memory 902 may also be an external storage device of the terminal device 900, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the terminal device 900. Further, the memory 902 may also include both an internal storage unit of the terminal device 900 and an external storage device. The memory 902 is used to store the computer program and other programs and data required by the terminal device. The memory 902 may also be used to temporarily store data that has been output or is to be output.

[0145] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the above-mentioned device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0146] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0147] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0148] In the embodiments provided in the present application, it should be understood that the disclosed devices / terminal equipment and methods can be implemented in other ways. For example, the device / terminal equipment embodiments described above are only schematic. For example, the division of the above modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or plug-ins can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0149] The units described above 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 units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0150] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0151] If the above-mentioned integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned various method embodiments, and can also be completed by instructing the relevant hardware through a computer program. The above-mentioned computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the above-mentioned computer program includes computer program code, and the above-mentioned computer program code can be in source code form, object code form, executable file or some intermediate form. The above-mentioned computer-readable medium may include: any entity or device capable of carrying the above-mentioned computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the above-mentioned computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0152] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or replace some of the technical features therein by equivalents. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A sight line recognition method, characterized in that: include: Acquire a first image, wherein the first image includes a preset reference object, and the preset reference object is an item carried by a vision detection user; Recognizing the shape of the preset reference object in the first image to obtain a first shape; If the first shape is different from the second shape, it is determined that the sight line of the vision detection user is not perpendicular to the sight mark, and the second shape is the shape of the preset reference object when the sight line of the vision detection user is perpendicular to the sight mark, wherein specifically includes: when the second shape is a circle, if the first shape is an ellipse, it is determined that the sight line of the vision detection user is not perpendicular to the sight mark; After determining that the sight line of the vision detection user is not perpendicular to the sight mark, the method further includes: Calculating the similarity between the first image and each preset image, where the preset image is a pre-stored image of the preset reference object rotated in a first direction; Determine the rotation direction corresponding to the preset image with the highest similarity as the first rotation direction; Determining a first rotation angle according to the first shape; wherein, when the first shape is an ellipse, determining the first rotation angle according to the first shape specifically includes: obtaining a first length of a minor axis and a second length of a major axis in the ellipse; calculating an arccosine value according to the first length and the second length to obtain the first rotation angle; According to the first rotation angle and the first rotation direction, an angle adjustment operation is performed on the sight mark so that the sight mark is perpendicular to the line of sight of the vision detection user, which specifically includes: controlling a display screen for displaying the sight mark to rotate the first rotation angle toward the first rotation direction.

2. The sight line recognition method according to claim 1, characterized in that: The sight mark is a three-dimensional sight mark; The performing an angle adjustment operation on the sight mark according to the first rotation angle and the first rotation direction includes: The three-dimensional sight mark is controlled to rotate in the first rotation direction by the first rotation angle.

3. The sight line recognition method according to claim 1, characterized in that: After determining that the sight line of the vision detection user is not perpendicular to the sight mark, the method further includes: Perform a prompting operation to prompt the vision testing user to stand in the vision testing area.

4. A sight line recognition device, characterized in that: include: A first image acquisition module, used to acquire a first image, wherein the first image includes a preset reference object, and the preset reference object is an item carried by the vision detection user; A recognition module, which recognizes the shape of the preset reference object in the first image to obtain a first shape; A determination module, configured to determine that the sight line of the vision detection user is not perpendicular to the sight mark if the first shape is different from the second shape, and the second shape is the shape of the preset reference object when the sight line of the vision detection user is perpendicular to the sight mark; wherein the determination module is configured to execute: when the second shape is a circle, if the first shape is an ellipse, then determine that the sight line of the vision detection user is not perpendicular to the sight mark; A calculation module, used for calculating the similarity between the first image and each preset image, wherein the preset image is a pre-stored image obtained by rotating the preset reference object in a first direction; A rotation direction determination module, used to determine the rotation direction corresponding to the preset image with the highest similarity as the first rotation direction; a rotation angle determination module, configured to determine a first rotation angle according to the first shape; wherein, when the first shape is an ellipse, the rotation angle determination module comprises: an acquisition unit, configured to acquire a first length of a minor axis and a second length of a major axis in the ellipse; and a calculation unit, configured to calculate an arccosine value according to the first length and the second length to obtain the first rotation angle; An angle adjustment module is used to perform an angle adjustment operation on the sight mark according to the first rotation angle and the first rotation direction, so that the sight mark is perpendicular to the line of sight of the vision detection user; wherein the angle adjustment module is used to execute: controlling the display screen used to display the sight mark to rotate a first rotation angle in the first rotation direction.

5. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 3 is implemented.

6. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 3 is implemented.

Images