Automatic training device combining overturning mirror and vision card

Abstract

The invention belongs to the technical field of visual training, and discloses an automatic training device combining a flip mirror and a visual card, which comprises a starting module, a camera module, a judgment module, a calculation module, an identification module and a statistics module. Whether a user sees the sighting mark clearly or not can be conveniently determined through the computer, and auxiliary personnel are not needed; the computer can be used for conveniently determining the time consumed by the user to use the positive and negative lenses and see the sighting mark clearly; the display scheme of the next sighting mark is dynamically and flexibly adjusted according to the observation result of the user on the sighting mark; the improvement degree can be conveniently observed and a treatment scheme can be conveniently revised by utilizing statistical data of a computer; the stickiness of the reverse racket used by a user is improved, especially for a child user.

Description

Technical Field

[0001] The invention belongs to the technical field of vision training, and in particular relates to an automatic training device combining a flip mirror and a vision card. Background Art

[0002] In the prior art, reversing mirrors and vision cards are commonly used vision training tools, which are mainly used to help users manually switch between positive and negative lenses and observe the sight marks on the vision cards to exercise eye muscles and restore and improve vision. Reversing mirrors usually consist of a pair of positive and negative lenses, which are located at one end of a handle respectively. Users switch by manually rotating the handle to adjust the eye focus. Vision cards are mostly paper, printed with sight marks of different sizes, contrasts and shapes, and users observe these sight marks in turn. Although this training method has been widely used, there are still many deficiencies in training accuracy, data tracking, personalized adjustment and user experience.

[0003] In the prior art, the main problems of reverse shooting and vision card can be divided into the following aspects:

[0004] 1. Subjectivity of User Observation Results

[0005] In traditional training methods, whether the user can clearly see the sight mark depends entirely on self-judgment, lacking objective evaluation. This method of relying on subjective feedback not only fails to accurately judge the user's actual observation situation, but may also cause the user to misjudge the observation effect, thus affecting the scientificity and effectiveness of the training effect. In addition, since there is no external verification method, it is difficult to evaluate the progress and effect of training.

[0006] 2. The observation time cannot be accurately counted

[0007] The time required for users to observe each sight mark cannot be accurately recorded, especially in the absence of assistants. It is not convenient for users to record the time by themselves, and it is easy to make mistakes. Even with assistants, manually recording the adjustment time for each sight mark is not only a lot of work, but also prone to errors due to negligence. Without statistical records of observation time, quantitative evaluation of training effects is also difficult to achieve, making the entire training process lack scientificity and data support.

[0008] 3. Lack of targeted sight mark adjustment

[0009] In existing paper vision card training, the type, size and difficulty of the sight mark are usually fixed. Users can only identify the sight marks one by one according to the standard process and cannot adjust according to their own training results. This fixed mode leads to poor training flexibility and difficulty in adapting to individual differences, which in turn affects the user's training enthusiasm. The fixed sight mark mode may also reduce training efficiency and make it difficult to achieve the optimal effect.

[0010] 4. Boring user experience and lack of feedback

[0011] In the existing training system, it is difficult for users to see their own progress, and the lack of data-supported feedback mechanism leads to a boring user experience. Due to the lack of data tracking of training progress, it is difficult for users to obtain an intuitive display of training effects, and it is difficult to persist in the long term, and the training effect is often affected. In addition, users lack scientific guidance during the operation process, resulting in a poor training experience and low user satisfaction.

[0012] 5. The distance between the sight mark and the reverse shot is difficult to control

[0013] In actual training, users need to maintain a reasonable distance between the reversing camera and the vision card to ensure the training effect. However, without an assistant, it is difficult for users to accurately grasp the appropriate observation distance, resulting in frequent changes in the distance between the sight mark and the reversing camera, thus affecting the training effect. Once the sight mark is too far or too close, the user's observation results may be inaccurate, which further affects the effect and scientificity of the training.

[0014] 6. It is difficult for assistants to operate

[0015] With the help of assistants, although the problem of recording the user's observation results and observation time can be solved to a certain extent, it still faces the problems of high difficulty in operation and low accuracy. Since there are multiple sight marks on the paper vision card, it is difficult for assistants to accurately track the sight mark that the user is observing, and it is also difficult to record the time manually. Since the sight marks are small and there are many of them, it is easy for assistants to make errors when recording and judging user feedback results, and the work is boring and difficult to sustain.

[0016] 7. Lack of quantitative evaluation of training data

[0017] The existing training system lacks a quantitative evaluation mechanism for training data, and cannot automatically generate data analysis and reports based on the user's training progress, resulting in users and assistants being unable to understand the user's actual progress. Without quantitative data support, it is difficult for users to make personalized adjustments to their training based on feedback data, and it is also difficult to scientifically evaluate the user's training results.

[0018] Some existing technical solutions have improved the function of the reversal shoot to a certain extent. For example, the invention patent CN104730730B "Head-mounted automatic flip glasses" authorized in 2017 designed a head-mounted device with automatic flip lenses, which can flip the lenses at a fixed time or frequency to avoid manual switching by users. However, this design does not solve the feedback problem between the vision card and the user's vision training process. The patent CN113940864B "A smart reversal shoot" authorized in 2022 describes a method of switching positive and negative lenses through an embedded system, but it mainly focuses on the automatic switching function of the reversal shoot, and does not involve the correctness judgment and time statistics of the user's observation results, as well as data analysis and personalized adjustment during the training process. Therefore, it is difficult for the existing technology to meet the needs of scientific and effective vision training.

[0019] Existing reverse shooting and vision card technologies have significant deficiencies in training accuracy, data statistics, user experience, and training personalization. It is difficult for users to obtain objective and quantitative data feedback during training, and it is impossible to dynamically adjust the training content according to personal progress. It is also difficult to control the training distance, which greatly reduces the training effect and experience. Existing technologies urgently need to be combined with modern sensing, data analysis, and intelligent adjustment technologies to improve the scientificity, effectiveness, and user satisfaction of training, thereby achieving optimization and innovation in vision training. Summary of the invention

[0020] In view of the problems existing in the prior art, the present invention provides an automatic training device combining a flip mirror and a vision card.

[0021] The present invention is achieved in that an automatic training device combining a flip mirror and a vision card comprises:

[0022] Startup module, camera module, judgment module, calculation module, recognition module, and statistics module;

[0023] A start-up module is connected to the camera module and is used to start the software, and then the software displays a prompt message to the user; the prompt message is "lift horizontally and reverse the camera to start the test".

[0024] The camera module is connected to the judgment module, and is used for the software to start observing whether the user holds the camera up horizontally and shoots reversely through the camera and image matching algorithm;

[0025] The judgment module is connected to the calculation module and is used by the software to judge whether the reverse shot is reversed through the camera and image matching algorithm.

[0026] The calculation module is connected with the start module, the camera module and the judgment module, and is used to calculate the distance between the reverse shot and the sight mark; by analyzing the reverse shot image, it is determined whether the user uses a positive lens or a negative lens; in the sight mark library, according to the user's statistical data (user's success rate, recognition time), according to the rules, the sight mark is selected, and the sight mark is displayed on the screen, and the time start is recorded; and the user is prompted to "speak or use gestures to indicate the direction of the sight mark"; and the user's observation result is waited for input;

[0027] The recognition module is connected to the computing module and is used for the software to recognize voice input through a voice recognition program; for gesture input, the software to recognize through image processing; and to determine whether the user has issued a stop voice or gesture;

[0028] The statistics module is connected to the calculation module and is used to display statistical information to the user, including the number of positive mirror tests, accuracy, average recognition time, and average distance; the number of negative mirror tests, accuracy, average recognition time, and average distance; and store the results for subsequent analysis.

[0029] Further, the step of waiting for the user to input the observation result includes:

[0030] a) User’s voice input;

[0031] b) User gesture input.

[0032] Another object of the present invention is to provide an automatic training method combining a flip mirror and a vision card, comprising:

[0033] Step 1: After the user starts the software, the software displays a prompt message to the user; the prompt message is "Lift horizontally and reverse the shot and reverse it to start the test";

[0034] Step 2: The software starts to observe whether the user holds the camera horizontally and shoots reversely through the camera and image matching algorithm;

[0035] If the software determines that the user is holding the camera horizontally and shooting reversely, it goes to step 3;

[0036] Otherwise, stay at step 2;

[0037] Step 3: The software uses the camera and image matching algorithm to determine whether the reverse shot is reversed.

[0038] If the judgment is not reversed, stay at step 3 and continue to judge;

[0039] If it is judged to be flipped, go to step 4;

[0040] Step 4: Calculate the distance between the reverse shot and the sight mark; by analyzing the image of the reverse shot, determine whether the user is using a positive lens or a negative lens;

[0041] In the optotype library, according to the user's statistical data (user's success rate, recognition time), according to the rules, select the optotype, display the optotype on the screen, record the time start; and prompt the user to "speak or use gestures to indicate the direction of the optotype";

[0042] Note: For example, if the positive mirror is found from the data, the error rate is high, so increase the test of the positive mirror; or enlarge the sight mark;

[0043] Waiting for the user to input observation results, including;

[0044] a) User’s voice input;

[0045] b) user’s gesture input;

[0046] When user input (voice or gesture) is detected, go to step 5; otherwise stay in the previous step;

[0047] Step 5: For voice input, the software recognizes it through a voice recognition program; for gesture input, the software recognizes it through image processing; and determines whether the user makes a stop voice or gesture;

[0048] a) If the user sends it, go to step 6;

[0049] b) If it is not issued, determine whether the user correctly says or indicates the direction of the sight mark, and record the result and time end;

[0050] c) Display the recognition result (correct or not), recognition time (time end of step 5 - time start of step 4), and recognition distance to the user; and prompt the user to "flip and reverse the photo" and proceed to step 4;

[0051] Step 6: Display statistical information to the user, including the number of positive mirror tests, accuracy, average recognition time, and average distance; the number of negative mirror tests, accuracy, average recognition time, and average distance; and store the results for subsequent analysis.

[0052] Another object of the present invention is to provide a computer device, which includes a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the automatic training method combining a flip mirror and a vision card.

[0053] Another object of the present invention is to provide a computer-readable storage medium storing a computer program, which, when executed by a processor, enables the processor to perform the steps of the automatic training method combining a flip mirror and a vision card.

[0054] Another object of the present invention is to provide an information data processing terminal, which is used to implement the automatic training device combining the flip mirror and the vision card.

[0055] In combination with the above technical solutions and the technical problems solved, the advantages and positive effects of the technical solutions to be protected by the present invention are as follows:

[0056] First, the present invention uses computer vision to identify the front and back sides of the reverse shot, or adds eye recognition based on the front and back side identification of the reverse shot to determine whether the user is using a positive mirror or a negative mirror; uses computer vision to calculate the distance between the reverse shot and the sight mark using the reverse shot image and the position of the sight mark on the screen; uses computer vision to observe user gestures, uses voice recognition to identify the user's voice, and combines the currently displayed sight mark to determine whether the user has correctly identified the sight mark; shows the user the distance of the sight mark, the correctness of the recognition result, and the recognition time each time the user observes; installs a strategy inside the computer to select the appropriate next sight mark based on the user's success rate and recognition time; and statistics the following according to the positive mirror and the negative mirror, respectively: average success rate, average recognition time, and average distance.

[0057] The present invention utilizes a computer to conveniently determine whether the user can see the visual mark clearly, without the need for an assistant; utilizes a computer to conveniently determine "the time consumed by the user to use the positive and negative lenses to see the visual mark clearly"; dynamically and flexibly adjusts the display plan of the next visual mark based on the user's observation results of the visual mark; utilizes the computer's statistical data to conveniently observe the degree of improvement and revise the treatment plan; and increases the stickiness of users in using the reverse camera, especially for children.

[0058] Second, the present invention solves some key technical problems existing in the prior art in industrial applications, especially the deficiencies in vision detection and training automation. Traditional vision detection equipment usually relies on manual operation, users need to manually adjust the equipment, and the training effect and accuracy depend on the experience of the operator. This not only increases the risk of errors, but also makes it difficult for detection efficiency and accuracy to meet industrial requirements. The present invention realizes efficient and accurate operation of vision detection through automated module design and multi-sensor fusion, overcoming the unstable factors caused by manual operation.

[0059] In industrial applications, the present invention automatically detects whether the user has raised and reversed the camera to take a photo through the collaborative work of the camera module and the judgment module, ensuring the accuracy of the operation specification and test. Traditional methods are difficult to automatically determine whether the operation is compliant, and there is a problem of inaccurate test data due to improper operation. The multi-module linkage of the present invention effectively solves this pain point, ensures the standardization and consistency of each test, significantly improves the reliability and accuracy of the test, and lays the foundation for industrial-scale application.

[0060] In addition, the present invention has achieved significant technical progress in data collection and statistical analysis. By integrating the statistical module, the system can record the user's test times, accuracy, recognition time and other key data in real time, and automatically store and feedback the data. This not only enables users to intuitively understand their test results, but also makes the data traceable and analyzable in industrial applications, providing a scientific basis for further vision training and improvement. Compared with the traditional method of manual recording, the present invention has made a qualitative improvement in data management and feedback efficiency.

[0061] In summary, the present invention has achieved significant technological progress in industrial applications and solved many problems in vision detection automation and data management. Its innovative multi-module integrated design and intelligent analysis methods enable the system to provide high-precision, standardized detection services, while simplifying the operation process and improving the user experience. In industrial applications, the automation and intelligent advantages of the present invention will bring great technological improvements and economic benefits to the vision detection industry.

[0062] Third, as auxiliary evidence of the inventiveness of the claims of the present invention, it is also reflected in the following important aspects:

[0063] (1) The expected benefits and commercial value of the technical solution of the present invention after transformation are:

[0064] The incidence of amblyopia in children in my country is 2% to 4%, and it has been increasing year by year. Some specific surveys and studies also support this data. For example, the results of the examination of 4-6-year-old children by the First Affiliated Hospital of Peking University Medical College showed that the incidence of amblyopia was 3%. Considering the birth rate of 10 million people, there are 300,000 new potential users each year.

[0065] The present invention provides an automatic training device, which is a new product and can effectively increase user stickiness and prevent users from not being serious in training; it can provide statistical information feedback to users at any time; and it can change the training plan according to the progress of the users, so as to improve the users' vision as quickly as possible.

[0066] Therefore, the social benefits (improved eyesight) and economic benefits (300,000 new potential users per year) are obvious.

[0067] (2) The technical solution of the present invention fills the technical gap in the industry at home and abroad:

[0068] The present invention provides an automatic training device, which is a new product and fills the gap in the domestic industry. Current products focus on the appearance of the reverse lens and the vision card, but do not link the two. The present invention is an intelligent vision card that can identify the reverse lens and has the functions of checking the positive and negative sides of the reverse lens (positive mirror and negative mirror); whether the sight mark is correctly identified; automatically adjusting the sight mark display scheme; and feeding back statistical information.

[0069] (3) Whether the technical solution of the present invention solves the technical problems that people have been eager to solve but have not been able to solve successfully:

[0070] For those who need vision training, after leaving the hospital, they usually carry a reversal camera and vision cards and need to go home to train on their own. Currently, reversal cameras and vision cards are not sticky enough for young patients, and they need someone to accompany and supervise them; during the process of self-training, young patients often move to the next sight mark without seeing it clearly, resulting in poor training results; due to the lack of statistical functions, young patients and their parents cannot get feedback in time (progress can be seen through hospital reexaminations, but it is not timely enough and often delays training progress).

[0071] (4) Whether the technical solution of the present invention overcomes technical prejudice:

[0072] In the field of reverse photogrammetry and vision cards, relevant practitioners have ignored the technological progress and cost reduction of computer vision and speech recognition. The present invention introduces computer vision and speech recognition into the field of reverse photogrammetry and vision cards and invents new products. BRIEF DESCRIPTION OF THE DRAWINGS

[0073] Figure 1 It is a structural block diagram of an automatic training device combining a flip mirror and a vision card provided by an embodiment of the present invention;

[0074] Figure 2 is a flow chart of an automatic training method combining a flip mirror and a vision card provided by an embodiment of the present invention;

[0075] Figure 3 This is a physical picture of a vision card provided by an embodiment of the present invention;

[0076] Figure 4 It is a reverse shot of a real object provided by an embodiment of the present invention;

[0077] Figure 5 Prompt information display at startup;

[0078] Figure 6 A sight mark display interface waiting for user voice input;

[0079] Figure 7 Error prompt interface when users report errors;

[0080] Figure 8 Correct feedback interface when user feedback is correct;

[0081] Fig. 9 Statistics feedback interface after the program ends.

[0082] Figure 1 In: 1. Start module; 2. Camera module; 3. Judgment module; 4. Calculation module; 5. Recognition module; 6. Statistics module. DETAILED DESCRIPTION

[0083] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0084] like Figure 1 As shown, an automatic training device combining a flip mirror and a vision card provided by an embodiment of the present invention comprises:

[0085] Startup module 1, camera module 2, judgment module 3, calculation module 4, recognition module 5, statistics module 6.

[0086] The start module 1 is connected to the camera module 2 and is used to start the software, and the software displays a prompt message to the user; the prompt message is "lift it horizontally and reverse it to start the test".

[0087] The camera module 2 is connected to the judgment module 3, and is used for the software to start observing whether the user raises the camera horizontally and shoots reversely through the camera and image matching algorithm;

[0088] The judgment module 3 is connected to the calculation module 4 and is used for the software to judge whether the reverse shot is reversed through the camera and image matching algorithm.

[0089] The calculation module 4 is connected with the start module 1, the camera module 2 and the judgment module 3, and is used to calculate the distance between the reverse shot and the sight mark; by analyzing the reverse shot image, it is determined whether the user uses a positive lens or a negative lens; in the sight mark library, according to the user's statistical data (the user's success rate, recognition time), according to the rules, the sight mark is selected, and the sight mark is displayed on the screen, and the time start is recorded; and the user is prompted to "speak or use gestures to indicate the direction of the sight mark"; and the user's observation result is waited for input;

[0090] The recognition module 5 is connected to the calculation module 4 and is used for the software to recognize the voice input through the voice recognition program; for the gesture input, the software to recognize it through image processing; and to determine whether the user has issued a stop voice or gesture;

[0091] The statistical module 6 is connected to the calculation module 4 and is used to display statistical information to the user, including the number of positive mirror tests, accuracy, average recognition time, and average distance; the number of negative mirror tests, accuracy, average recognition time, and average distance; and store the results for subsequent analysis.

[0092] The automatic training device combined with the flip mirror and the vision card provided in the embodiment of the present invention is mainly used to help users to test and train their vision. Through the coordinated action of the camera module, the judgment module, the calculation module and the recognition module, the automatic recognition of the user's flip-shot operation and the recognition of the sight mark are realized. The following is the detailed working principle of the device.

[0093] The startup module is responsible for starting the software and providing the user with initial prompts. After the user starts the software, the startup module 1 displays prompt information on the screen to guide the user to raise the camera horizontally and perform the reverse operation. The prompt information is, for example, "After raising the camera horizontally and performing the reverse operation, start the test" to ensure that the user understands the test process and operation requirements. This prompt helps ensure that the user enters the correct preparation state and prepares for the subsequent observation and judgment of the camera module.

[0094] The camera module 2 monitors the user's operation in real time through the device's camera. After the user raises the flip racket, the camera module captures the image of the user holding the flip racket, and identifies the direction and position of the flip racket through the image matching algorithm to ensure that the user operates correctly according to the prompts. The image matching algorithm of this module can accurately determine whether the user holds the flip racket horizontally. Only when the conditions are met will the software proceed to the next step to ensure that the test is accurate.

[0095] The judgment module 3 determines whether the reverse shot has been reversed by the user through the image recognition algorithm based on the image data provided by the camera module 2. After the judgment module recognizes that the user has completed the reversal operation, the calculation module will be allowed to continue processing to ensure that the user's operation meets the test requirements. If the user operation is not completed, the system will continue to monitor until the user correctly completes the reversal, ensuring the standardized operation of the test.

[0096] After confirming the reverse state of the reverse shot, the calculation module 4 will calculate the distance between the reverse shot and the sight mark. This module analyzes the reverse shot image captured by the camera, determines whether the user is currently using a positive lens or a negative lens, and selects an appropriate sight mark in the sight mark library based on statistical data (such as the user's success rate and recognition time). After selecting the sight mark, the calculation module displays it on the screen, starts timing, and records the start time of the test. Subsequently, the system prompts the user to "say or use gestures to indicate the direction of the sight mark" to guide the user to perform observation and feedback operations.

[0097] The recognition module 5 is used to recognize the user's input results, including voice and gestures. For voice input, the recognition module converts the user's voice content into recognizable text through a voice recognition program; for gesture input, the system recognizes the user's gesture through an image processing algorithm. The recognition module also determines whether the user issues a voice or gesture command to stop the test. If the user issues a "stop" command, the system will terminate the test and record the current data to ensure that the user can terminate or continue the test according to their needs.

[0098] After the test, the statistics module 6 collects and displays the user's test result information, including the number of positive and negative lens tests, accuracy, average recognition time and average distance. Through these statistical data, the user can understand his or her performance in the test, and these data will be stored for subsequent analysis. The records of the statistics module help the user and the doctor or professional to check the user's vision training status and progress in the future, and provide data support for further training and treatment plans.

[0099] The method of waiting for the user to input the observation result provided by the embodiment of the present invention includes:

[0100] a) User’s voice input;

[0101] b) User gesture input.

[0102] like Figure 2 As shown, an automatic training method combining a flip mirror and a vision card provided by an embodiment of the present invention includes:

[0103] S101: After the user starts the software, the software displays a prompt message to the user; the prompt message is "lift horizontally and reverse the shot and reverse, then start the test";

[0104] S102: The software starts to observe whether the user holds the camera up horizontally and shoots reversely through the camera and image matching algorithm;

[0105] If the software determines that the user holds the camera horizontally and reverses the camera, the software proceeds to S103;

[0106] Otherwise, stay at S102;

[0107] S103: The software determines whether the reverse shot is reversed through the camera and the image matching algorithm;

[0108] If it is determined that there is no flip, stay in S103 and continue to judge;

[0109] If it is determined to be flipped, go to S104;

[0110] S104: Calculate the distance between the reverse shot and the sight mark; and determine whether the user uses a positive lens or a negative lens by analyzing the image of the reverse shot;

[0111] In the optotype library, according to the user's statistical data (user's success rate, recognition time), according to the rules, select the optotype, display the optotype on the screen, record the time start; and prompt the user to "speak or use gestures to indicate the direction of the optotype";

[0112] Note: For example, if the positive mirror is found from the data, the error rate is high, so increase the test of the positive mirror; or enlarge the sight mark;

[0113] Waiting for the user to input observation results, including;

[0114] a) User’s voice input;

[0115] b) user’s gesture input;

[0116] When user input (voice or gesture) is detected, proceed to S105; otherwise, stay at the previous step;

[0117] S105: For voice input, the software recognizes it through a voice recognition program; for gesture input, the software recognizes it through image processing; and determines whether the user makes a stop voice or gesture;

[0118] a) If the user sends it, proceed to S106;

[0119] b) If it is not issued, determine whether the user correctly says or indicates the direction of the sight mark, and record the result and time end;

[0120] c) showing the user the recognition result (correct or not), recognition time (end of S105 - start of S104), and recognition distance; and prompting the user to "flip and reverse the photo" to enter S104;

[0121] S106: Display statistical information to the user, including the number of positive mirror tests, accuracy, average recognition time, and average distance; the number of negative mirror tests, accuracy, average recognition time, and average distance; and store the results for subsequent analysis.

[0122] Another object of the present invention is to provide a computer device, which includes a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the automatic training method combining a flip mirror and a vision card.

[0123] Another object of the present invention is to provide a computer-readable storage medium storing a computer program, which, when executed by a processor, enables the processor to perform the steps of the automatic training method combining a flip mirror and a vision card.

[0124] Another object of the present invention is to provide an information data processing terminal, which is used to implement the automatic training device combining the flip mirror and the vision card.

[0125] The working principle of the present invention is based on an intelligent vision training system, which realizes automatic interaction and data collection and analysis between users, reverse cameras and vision cards through the combination of computer equipment and software programs. The entire system is mainly composed of a prompt module, an image recognition module, a voice or gesture recognition module, a distance detection module, a sight mark selection module and a data statistics module, which guides users to complete the training process step by step, and records and analyzes the user's performance data in real time.

[0126] First, after the user starts the system, the software program displays a prompt message to guide the user to raise the flip racket horizontally and prepare for flipping. While prompting the user, the camera and image recognition module are activated, and the image matching algorithm is used to monitor the posture of the flip racket in the user's hand to determine whether it has reached a horizontal state. Only after the system confirms that the user has raised the flip racket horizontally will it proceed to the next step, otherwise the software will stay at this stage to ensure that the user's starting posture is correct.

[0127] Next, the system enters the flip detection stage. The user starts to manually flip the reverse camera, and the image recognition module analyzes the state of the reverse camera in real time to determine whether the positive lens and the negative lens have been switched. After the system recognizes that the lens is flipped, it automatically determines whether the current lens is a positive lens or a negative lens, and measures the distance between the reverse camera and the vision card. This distance information will be used for subsequent analysis of training results to ensure that users maintain a reasonable viewing distance.

[0128] After the lens status is determined, the sight mark selection module starts working. The system selects the sight mark based on the user's previous training data (including accuracy and recognition time). For example, if the user performs poorly in the positive lens training, the system will increase the number of positive lens training times or increase the sight mark size to meet the user's training needs. After the sight mark is displayed on the screen, the system records the time point when recognition starts (start) and prompts the user to use voice or gestures to indicate the direction of the sight mark.

[0129] The user inputs the observation results through voice or gesture, and the system analyzes and interprets them through the voice recognition and gesture recognition modules. The recognition results are divided into three situations: if the user issues a stop command, the system will end the training and enter the statistical phase; if the user correctly points out the direction of the sight mark, the system records the correct result and the end time (end), and shows the user the recognition accuracy, recognition time and sight mark distance; if the user inputs incorrectly, the system records the incorrect result, also shows the relevant information to the user, and guides the user to flip and reverse the shot again, and repeat the above process.

[0130] After the training is completed, the system enters the data statistics stage. The system will collect and display various data of the positive and negative lenses in the current training to the user, including the number of positive and negative lens tests, average recognition time, accuracy, and average recognition distance. These statistical data will also be stored in the system for subsequent data analysis and provide a basis for future training plans.

[0131] The present invention is specifically implemented:

[0132] Figure 3 The existing vision cards are mainly paper, with multiple sight marks (such as) printed on them for users to read;

[0133] Figure 4 It is a reverse racket (flip mirror, flip racket) comprising a pair of positive mirrors and a pair of negative mirrors, each located at one end of the handle.

[0134] The present invention is composed of a computer (including a camera), software and a reverse camera (flip mirror, flip camera). Its working process is as follows:

[0135] Step 1: After the user starts the software, the software displays a prompt message to the user;

[0136] The prompt message is "Lift horizontally, reverse the shot and reverse it, then start the test";

[0137] Step 2: The software starts to observe whether the user holds the camera horizontally and shoots reversely through the camera and image matching algorithm;

[0138] 2.1 If the software determines that the user is holding the camera up horizontally and flipping it, go to step 3;

[0139] 2.2 Otherwise, stay at step 2;

[0140] Step 3: The software uses the camera and image matching algorithm to determine whether the reverse shot is reversed.

[0141] If the judgment is not reversed, stay at step 3 and continue to judge;

[0142] If it is judged to be flipped, go to step 4;

[0143] Step 4:

[0144] 4.1 Calculate the distance between the reverse beat and the sight mark;

[0145] 4.2 By analyzing the reverse-shot images, determine whether the user is using a positive or negative lens;

[0146] 4.3 In the optotype library, according to the user's statistical data (user's success rate, recognition time), select an optotype according to the rules, display the optotype on the screen, and record the time start; and prompt the user to "speak or use gestures to indicate the direction of the optotype";

[0147] Note: For example, if the positive mirror is found from the data, the error rate is high, so increase the test of the positive mirror; or enlarge the sight mark;

[0148] 4.4 Waiting for the user to input observation results, including;

[0149] a) User’s voice input;

[0150] b) user’s gesture input;

[0151] 4.5 When user input (voice or gesture) is detected, go to step 5; otherwise stay at 4.4;

[0152] Step 5:

[0153] 5.1 For voice input, the software recognizes it through a voice recognition program; for gesture input, the software recognizes it through image processing;

[0154] 5.2 Determine whether the user makes a stop voice or gesture

[0155] a) If the user sends it, go to step 6;

[0156] b) If it is not issued, determine whether the user correctly says or indicates the direction of the sight mark, and record the result and time end;

[0157] c) Display the recognition result (correct or not), recognition time (time end of step 5 - time start of step 4), and recognition distance to the user; and prompt the user to "flip and reverse the photo" and proceed to step 4;

[0158] Step 5: Display statistical information to the user, including the number of positive mirror tests, accuracy, average recognition time, and average distance; the number of negative mirror tests, accuracy, average recognition time, and average distance; and store the results for subsequent analysis.

[0159] Figure 5 Prompt message display at startup

[0160] When the system starts, a prompt message is displayed on the screen to guide the user to hold the reverse racket horizontally and prepare to flip. The prompt content is "After holding the reverse racket horizontally and flipping it, start the test."

[0161] Figure 6 The sight mark display interface waiting for user voice input

[0162] After the system confirms that the user has raised the reverse racket and flipped it, the corresponding sight mark is displayed on the screen, and the user is prompted to input the observation results of the sight mark through voice or gesture.

[0163] Figure 7 Error prompt interface when user reports an error

[0164] When the system recognizes that the user's feedback is incorrect (the direction or content of the visual mark is not correctly identified), an error prompt is displayed on the screen, pointing out that the user's recognition result is incorrect, and guiding the user to continue training.

[0165] Figure 8 Correct feedback interface when user feedback is correct

[0166] If the user successfully identifies the direction or content of the sight mark, the system displays correct feedback information on the screen to confirm the user's correct result and record the recognition time and distance data.

[0167] Fig. 9 Statistics feedback interface after the program ends

[0168] After the training is completed, the system displays the user's training statistics, including the number of positive and negative mirror tests, accuracy, average recognition time, and recognition distance, providing the user with overall feedback on the training.

[0169] The application field of the present invention is: vision training.

[0170] The existing products are reversing cameras (manual, electric, and deformed) and paper vision cards (printed with many sight marks). Users use reversing cameras, alternately use positive and negative lenses, observe the sight marks on the vision cards, and train their vision.

[0171] The product of the present invention provides a device to replace the vision card. This device can monitor the flipping of the reverse shot and determine whether the user is using a positive lens or a negative lens; display visual marks under algorithm control based on user feedback; recognize the user's gestures or sounds to determine whether the user has recognized correctly; and count relevant information, etc.

[0172] In the existing products of "reverse shooting (manual, electric, deformed in appearance) and paper vision cards (printed with many sight symbols)", users read the sight symbols independently. There is no way to judge whether the user's observation results are correct, it is impossible to display the sight symbols and adjust the training plan based on user feedback, and it is also impossible to collect various information.

[0173] The device of the present invention is equivalent to a smart vision card, which can determine whether the user is using a positive lens or a negative lens; judge the user's observation results; display visual marks and adjust the training plan according to user feedback; and count various information, which can effectively increase the user's stickiness in using the device and improve the user's vision as soon as possible.

[0174] It should be noted that the embodiments of the present invention can be implemented by hardware, software, or a combination of software and hardware. The hardware part can be implemented using dedicated logic; the software part can be stored in a memory and executed by an appropriate instruction execution system, such as a microprocessor or dedicated design hardware. It can be understood by a person of ordinary skill in the art that the above-mentioned devices and methods can be implemented using computer executable instructions and / or contained in a processor control code, such as a carrier medium such as a disk, CD or DVD-ROM, a programmable memory such as a read-only memory (firmware), or a data carrier such as an optical or electronic signal carrier. Such code is provided on the carrier medium. The device and its modules of the present invention can be implemented by hardware circuits such as very large-scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, etc., or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc., can also be implemented by software executed by various types of processors, and can also be implemented by a combination of the above-mentioned hardware circuits and software, such as firmware.

[0175] The above description is only a specific implementation mode of the present invention, but the protection scope of the present invention is not limited thereto. Any modifications, equivalent substitutions and improvements made by any technician familiar with the technical field within the technical scope disclosed by the present invention and within the spirit and principle of the present invention should be covered by the protection scope of the present invention.

Claims

1. An automatic training device combining a flip mirror and a vision card, characterized in that: include: The start module is connected to the camera module and is used to start the software. The software displays a prompt message to the user, which is "lift horizontally and reverse the camera to start the test"; The camera module is connected to the judgment module, and is used for the software to observe whether the user holds the camera up horizontally and shoots reversely through the camera and image matching algorithm; The judgment module is connected to the calculation module and is used for the software to judge whether the reverse shot is flipped through the camera and the image matching algorithm; The calculation module is connected with the start module, the camera module and the judgment module, and is used to calculate the distance between the reverse shot and the sight mark; judge whether the user uses a positive lens or a negative lens by analyzing the reverse shot image; and select a sight mark from the sight mark library according to the user's statistical data, and display the sight mark on the screen, record the time start, and prompt the user to "say or use gestures to indicate the direction of the sight mark", and wait for the user to input the observation result; A recognition module, connected to the calculation module, for recognizing the voice input through a voice recognition program, or recognizing the gesture input through image processing, and determining whether the user has issued a stop voice or gesture; The statistical module is connected to the calculation module and is used to display statistical information to the user, including the number of tests of the positive mirror and the negative mirror, the accuracy, the average recognition time and the average distance, and store the results for subsequent analysis.

2. The automatic training device combining a flip mirror and a vision card as claimed in claim 1, characterized in that: The step of waiting for the user to input the observation result comprises: a) User’s voice input; b) User gesture input.

3. The automatic training device combining a flip mirror and a vision card as claimed in claim 1, characterized in that: The calculation module is used to select the sight mark according to the user's statistical data and preset rules, including adjusting the difficulty of the sight mark based on the user's success rate and recognition time in the positive mirror and negative mirror tests.

4. The automatic training device combining a flip mirror and a vision card as claimed in claim 1, characterized in that: The statistical module is used to generate a detailed statistical report of the positive mirror and negative mirror test, which includes the number of positive mirror and negative mirror tests, accuracy, average recognition time and average distance, and stores the statistical results in the device memory for use by users and subsequent analysis.

5. An automatic training method combining a flip mirror and a vision card according to any one of claims 1 to 4, characterized in that: The automatic training method combining the flip mirror and the vision card comprises: Step 1: After the user starts the software, the software displays a prompt message to the user; the prompt message is "Lift horizontally and reverse the shot and reverse it, then start the test"; Step 2: The software starts to observe whether the user holds the camera horizontally and shoots reversely through the camera and image matching algorithm; If the software determines that the user is holding the camera horizontally and shooting reversely, it goes to step 3; Otherwise, stay at step 2; Step 3: The software uses the camera and image matching algorithm to determine whether the reverse shot is reversed. If the judgment is not reversed, stay at step 3 and continue to judge; If it is judged to be flipped, go to step 4; Step 4: Calculate the distance between the reverse shot and the sight mark; by analyzing the image of the reverse shot, determine whether the user is using a positive lens or a negative lens; In the optotype library, according to the user's statistical data and rules, select the optotype, display it on the screen, and record the time start; and prompt the user to "speak or use gestures to indicate the direction of the optotype"; Note: For example, if the positive mirror is found from the data, the error rate is high, so increase the test of the positive mirror; or enlarge the sight mark; Waiting for the user to input observation results, including; a) User’s voice input; b) user’s gesture input; When user input is detected, go to step 5; otherwise stay in the previous step; Step 5: For voice input, the software recognizes it through a voice recognition program; for gesture input, the software recognizes it through image processing; and determines whether the user makes a stop voice or gesture; a) If the user sends it, go to step 6; b) If it is not issued, determine whether the user correctly says or indicates the direction of the sight mark, and record the result and time end; c) Display the recognition result, recognition time, and recognition distance to the user; and prompt the user to "flip and reverse the photo" and proceed to step 4; Step 6: Display statistical information to the user, including the number of positive mirror tests, accuracy, average recognition time, and average distance; the number of negative mirror tests, accuracy, average recognition time, and average distance; and store the results for subsequent analysis.

6. A computer device, characterized in that: The computer device includes a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the automatic training method combining a flip mirror and a vision card as claimed in claim 5.

7. A computer-readable storage medium storing a computer program, wherein when the computer program is executed by a processor, the processor executes the steps of the automatic training method combining a flip mirror and a vision card as claimed in claim 5.

8. An information data processing terminal, characterized in that: The information data processing terminal is used to implement the automatic training device combining a flip mirror and a vision card as described in any one of claims 1-4.

Images