Image acquisition device and method for skiascopy optometry

Abstract

The invention provides a retinoscopy image acquisition device and method, the device comprises a fixing assembly, a retinoscopy, a camera, a three-axis motion platform and a base, the fixing assembly comprises a retinoscopy fixing seat and a camera fixing seat which are connected through a connecting piece; the retinoscope is connected with the retinoscope fixing seat, the camera is connected with the camera fixing seat, the camera fixing seat is connected with the retinoscope fixing seat through a connecting piece, and the camera is located behind the retinoscope and right faces a retinoscope observation hole; the fixing assembly is connected with the three-axis motion platform and can move in three directions under the driving of the three-axis motion platform, the three-axis motion platform is connected with the base, and the forehead support fixator is connected to the base; the skiascope can stably move in three directions, errors caused by human factors of an optometrist are eliminated, the skiascope moving direction can be automatically and rapidly obtained, the optometrist or subsequent algorithm processing analysis is facilitated, and skiascope optometry automation and intelligence are achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of retinoscopy, and in particular to an image acquisition device for retinoscopy, an image acquisition control method for retinoscopy, an image acquisition control system for retinoscopy, a computer terminal, a computer-readable storage medium and a computer program product. Background Art

[0002] The statements in this section merely provide background art related to the present invention and do not necessarily constitute prior art.

[0003] The eye is one of the most important sensory organs of the human body, and visual quality is crucial to an individual's quality of life. In recent years, the number of patients with refractive errors has been gradually increasing. Retinoscopy is a key method used to measure and analyze the refractive power and astigmatism of the eyeball to determine the appropriate glasses or contact lenses.

[0004] However, the inventors have found that the traditional retinoscopy method requires a professionally trained optometrist to operate it, and the optometrist needs to hold the retinoscope. During the retinoscopy process, the distance between the retinoscope and the patient and the stability of movement cannot be well guaranteed, and the neutral point cannot be quickly and accurately identified and confirmed. There may be measurement errors, resulting in inaccurate vision correction. Summary of the invention

[0005] In order to address the deficiencies in the prior art, the present invention provides an image acquisition device and method for retinoscopy, which achieves stable movement of the retinoscope in three directions, eliminates errors caused by human factors of optometrists, can automatically and quickly obtain the direction of shadow movement and determine the position of the neutral point, is convenient for optometrists or subsequent algorithm processing and analysis, and realizes the automation and intelligence of retinoscopy.

[0006] In order to achieve the above object, the present invention adopts the following technical solution:

[0007] In a first aspect, the present invention provides an image acquisition device for retinoscopy.

[0008] An image acquisition device for retinoscopy optometry comprises: a fixing assembly, a retinoscope, a camera, a three-axis motion platform and a base, wherein the fixing assembly comprises a retinoscope fixing seat and a camera fixing seat connected by a connecting piece;

[0009] The retinoscope is connected to the retinoscope fixing seat, the camera is connected to the camera fixing seat, the camera fixing seat is connected to the retinoscope fixing seat through a connecting piece, the camera is located behind the retinoscope and the camera is facing the retinoscope observation hole;

[0010] The fixing component is connected to the three-axis motion platform and can move in three directions driven by the three-axis motion platform. The three-axis motion platform is connected to the base, and a forehead support fixer is connected to the base.

[0011] As a further limitation of the first aspect of the present invention, the motor module of the three-axis motion platform is fixed on the base, the motor module is connected to the motor controller, the motor controller is fixed on the base, and the motor controller, the camera and the retinoscope are respectively connected to the computer terminal.

[0012] As a further limitation of the first aspect of the present invention, the base includes a bottom plate and a base shell, the bottom plate and the base shell are connected, and the bottom plate is connected to the forehead support fixer.

[0013] In a second aspect, the present invention provides an image acquisition control method for retinoscopy.

[0014] A method for controlling image acquisition of retinoscopy optometry, using the image acquisition device of retinoscopy optometry according to the first aspect of the present invention, comprises the following steps:

[0015] Get the video stream of the camera, perform face recognition on the video stream frame by frame, identify the eye area, and record the coordinates of the center point of the eye area frame by frame. Compare the coordinates of the center point of the eye area in the last N seconds, where N is greater than or equal to 1. If the change in the coordinates of the center point of the eye area is less than or equal to the set threshold, execute the next step, otherwise return to the previous step to re-acquire the video stream of the camera;

[0016] Control the three-axis motion platform to move the retinoscope to a position at a first set distance from the patient, and then execute left and right movement instructions to obtain the optometry video stream;

[0017] The optometry video stream is processed frame by frame, the eye area is identified, and then cropped to retain only the eye area image to obtain the eye area image sequence, which is then input into the classification network for identification to obtain the forward motion, reverse motion, and neutralization judgment results;

[0018] If the recognition result is neutral, the three-axis motion platform is controlled so that the retinoscope is close to the test person and the distance between it and the test person is less than the first set distance, and then it moves left and right to obtain the optometry video stream and execute the previous judgment process again to obtain the first shadow motion result when close to the test person; the motor module for three-axis movement is controlled so that the retinoscope is away from the test person and the distance between it and the test person is greater than the first set distance, and then it moves left and right to obtain the optometry video stream and execute the previous judgment process again to obtain the second shadow motion result when away from the test person. If the first shadow motion result is forward motion and the second shadow motion result is reverse motion, it is confirmed as the neutral point, otherwise it is determined that it cannot be determined and the camera video stream is acquired again.

[0019] As a further limitation of the second aspect of the present invention, an Encoder-Decoder structure is used to perform feature extraction and dimensionality reduction on the input eye area image sequence to obtain an eye image feature sequence, and the eye image feature sequence is input into the RNN for classification to obtain forward motion, reverse motion and neutralization judgment results.

[0020] In a third aspect, the present invention provides an image acquisition control system for retinoscopy, using the image acquisition device for retinoscopy described in the first aspect of the present invention, including the following process:

[0021] The data acquisition unit is configured to: acquire the video stream of the camera, perform face recognition on the video stream frame by frame, identify the eye area, and record the coordinates of the center point of the eye area frame by frame, and compare the coordinates of the center point of the eye area in the last N seconds, where N is greater than or equal to 1. If the change amplitude of the coordinates of the center point of the eye area is less than or equal to a set threshold, execute the process of the optometry control unit, otherwise return to re-acquire the video stream of the camera;

[0022] The optometry control unit is configured to: control the three-axis motion platform, move the retinoscope to a position at a first set distance from the patient, and then execute left and right movement instructions to obtain an optometry video stream;

[0023] The shadow motion judgment unit is configured to: process the optometry video stream frame by frame, identify the eye area, and crop it to retain only the eye area image to obtain an eye area image sequence, input the eye area image sequence into the classification network for recognition, and obtain the judgment results of forward motion, reverse motion, and neutralization;

[0024] The neutralization judgment unit is configured as follows: if the recognition result is neutralization, the three-axis motion platform is controlled so that the retinoscope is close to the tester and the distance between the retinoscope and the tester is less than a first set distance, and then the left and right movements are performed to obtain the optometry video stream and the judgment process of the shadow motion judgment unit is performed again to obtain the first shadow motion result when close to the tester; the motor module for three-axis movement is controlled so that the retinoscope is away from the tester and the distance between the retinoscope and the tester is greater than a first set distance, and then the left and right movements are performed to obtain the optometry video stream and the judgment process of the shadow motion judgment unit is performed again to obtain the second shadow motion result when away from the tester. If the first shadow motion result is a forward motion and the second shadow motion result is a reverse motion, it is confirmed as a neutralization point, otherwise it is determined that it cannot be determined and the camera video stream acquisition is performed again.

[0025] As a further limitation of the third aspect of the present invention, in the motion judgment unit, an Encoder-Decoder structure is used to perform feature extraction and dimensionality reduction on the input eye area image sequence to obtain an eye image feature sequence, and the eye image feature sequence is input into the RNN for classification to obtain forward motion, reverse motion and neutralization judgment results.

[0026] In a fourth aspect, the present invention provides a computer terminal, comprising: a processor and a computer readable storage medium;

[0027] a processor adapted to execute a computer program;

[0028] A computer-readable storage medium, wherein a computer program is stored in the computer-readable storage medium, and when the computer program is executed by the processor, the image acquisition control method for retinoscopy as described in the second aspect of the present invention is implemented.

[0029] In a fifth aspect, the present invention provides a computer-readable storage medium storing a computer program, wherein the computer program is suitable for being loaded by a processor and executing the image acquisition control method for retinoscopy as described in the second aspect of the present invention.

[0030] In a sixth aspect, the present invention provides a computer program product, which includes a computer program. When the computer program is executed by a processor, it implements the image acquisition control method for retinoscopy as described in the second aspect of the present invention.

[0031] Compared with the prior art, the present invention has the following beneficial effects:

[0032] 1. The present invention innovatively develops an image acquisition device for retinoscopy, which realizes the stable movement of the retinoscope in three directions. The camera is located behind the retinoscope and faces the observation hole of the retinoscope, eliminating the error caused by the human factor of the optometrist.

[0033] 2. The present invention innovatively proposes an image acquisition control method for retinoscopy, which can automatically and quickly obtain a more accurate shadow movement direction through repeated judgment of the neutral point, which is convenient for optometrists or subsequent algorithm processing and analysis, thereby realizing the automation and intelligence of retinoscopy.

[0034] Advantages of additional aspects of the present invention will be given in part in the following description, and in part will become obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0036] Figure 1 A schematic diagram of the three-dimensional structure of the image acquisition device for retinoscopy provided in Embodiment 1 of the present invention;

[0037] Figure 2 A schematic diagram of a fixing assembly provided in Example 1 of the present invention;

[0038] Figure 3 A schematic diagram of a base provided in Example 1 of the present invention;

[0039] Figure 4 A schematic diagram of a three-axis motor module provided in Example 1 of the present invention;

[0040] Figure 5 A schematic flow chart of an image acquisition control method for retinoscopy provided in Embodiment 2 of the present invention;

[0041] Figure 6 A schematic diagram of an image acquisition control system for retinoscopy provided in Embodiment 3 of the present invention;

[0042] Figure 7 A schematic diagram of an electronic device provided in Embodiment 4 of the present invention;

[0043] Among them, 1-fixing component; 101-retinoscope holder; 102-camera holder; 103-connecting piece; 2-base; 201-base shell; 202-bottom plate; 203-forehead support holder; 3-three-axis motion motor module; 301-platform; 302-motor module for motion in the X-axis direction; 303-motor module for motion in the Y-axis direction; 304-motor module for motion in the Z-axis direction. DETAILED DESCRIPTION

[0044] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0045] It should be noted that the following detailed descriptions are exemplary and are intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.

[0046] In the absence of conflict, the embodiments of the present invention and the features of the embodiments may be combined with each other.

[0047] Embodiment 1:

[0048] like Figure 1 As shown, the present implementation proposes an image acquisition device for retinoscopy, including a fixed component 1, a base 2, a three-axis motion motor module 3 (i.e., a three-axis motion platform, other three-axis modules may also be used, as long as the three-axis motion line of sight can be realized, which will not be repeated here) and a computer terminal, wherein the fixed component 1 is fixed on the platform 301 of the three-axis motion motor module 3, and the three-axis motion motor module 3 is fixed on the base 2.

[0049] like Figure 2As shown, the retinoscope holder 101 is located in front of the camera holder 102, and the retinoscope holder 101 is connected to the camera holder 102 through a connector 103. The threaded hole in front of the retinoscope holder 101 can be used to fix retinoscopes of different sizes with screws, and the threaded hole above the camera holder 102 can be used to fix the camera with screws. The rectangular opening on the right side can be used for data cables to pass through. The rear of the connector 103 is fixed to the platform 301 by screws, and is moved by the three-axis motion motor module 3.

[0050] like Figure 3 As shown, the base 2 includes a base shell 201, a bottom plate 202 and a forehead rest fixer 203. The bottom plate 202 is connected to the base shell 201 and serves as a supporting structure. The forehead rest fixer 203 is located in front of the base shell and extends out to fix the forehead rest.

[0051] like Figure 4 As shown, the three-axis motion motor module includes a platform 301, a motor module 302 for motion in the X-axis direction, a motor module 303 for motion in the Y-axis direction, and a motor module 304 for motion in the Z-axis direction.

[0052] In the present implementation, preferably, the motor module 302 moving in the X-axis direction, the motor module 303 moving in the Y-axis direction and the motor module 304 moving in the Z-axis direction all adopt a slide rail-slider structure, and the slider is driven to move along the slide rail by different transmission methods; the platform 301 is fixed on the slider of the motor module 304 moving in the Z-axis direction, and can be driven to move up and down along the Z-axis by the motor module 304 moving in the Z-axis direction through the transmission method of a ball screw, the motor module 304 moving in the Z-axis direction is fixed on the slider of the motor module 302 moving in the X-axis direction, and is driven to move left and right along the X-axis direction by the motor module 302 moving in the X-axis direction through a belt transmission method; the motor module 302 moving in the X-axis direction is fixed on the slider of the motor module 303 moving in the Y-axis direction, and is driven to move forward and backward along the Y-axis by the motor module 303 moving in the Y-axis direction through a belt transmission method. The three-axis motion motor module 3 is equipped with a controller, and a control command is sent to the controller through a computer terminal. The controller controls the motor movements in the motor module 302 for motion in the X-axis direction, the motor module 303 for motion in the Y-axis direction, and the motor module 304 for motion in the Z-axis direction, thereby realizing the movement of the platform 301 and the fixed component 1 on three axes.

[0053] The computer terminal in the present implementation can be a general-purpose computer, which has the functions of human-computer interaction and running programs, and has a communication interface. The communication interface on the general-purpose computer is connected to the camera and the controller respectively through a data cable. Software is running on the general-purpose computer. The software can send different control commands or their combinations to the controller through the communication interface, thereby realizing various movement modes of the retinoscope and the camera holder, including speed adjustment, direction adjustment, and reciprocating motion, etc.; during the entire movement process, the software can obtain the video stream of the camera through the communication interface, and display and save it in real time; in addition, the software is configured with automatic acquisition and image processing algorithms. After the tester puts his chin on the forehead rest, it will automatically control the hardware equipment to shoot the eye examination video, and calculate the direction of the shadow movement, and the output is displayed on the software interface.

[0054] When the above-mentioned acquisition device of the present invention is actually used, the retinoscope is fixed on the retinoscope holder 101, and the retinoscope can be fixed by screws through the threaded hole in the front, the camera is fixed on the camera holder 102, and the camera can be fixed by screws through the threaded hole on the top, the forehead rest is fixed on the forehead rest holder 203, the camera and the three-axis motion motor module 3 are respectively connected to the communication interface of the computer terminal through data cables, and the three-axis motion motor module 3 needs to be additionally connected to a power supply. The subject places his chin on the forehead rest, and the optometrist controls the three-axis motion of the retinoscope and the camera through the software on the computer terminal. In the whole motion process, the image seen through the observation hole of the retinoscope can be recorded by the camera and transmitted to the computer terminal, and displayed and saved in real time on the software; in addition to the manual control method, the software has built-in automatic acquisition and image processing algorithms, which can control the equipment to automatically acquire and save the optometry video, and then calculate the direction of the shadow movement to provide a reference for the optometrist.

[0055] Embodiment 2:

[0056] like Figure 5 As shown, this implementation provides an image acquisition control method for retinoscopy, using the image acquisition device for retinoscopy described in Example 1 of the present invention, including the following process:

[0057] S1: Obtain the video stream of the camera, perform face recognition on the video stream frame by frame, identify the eye area, and record the coordinates of the center point of the eye area frame by frame, and compare the coordinates of the center point of the eye area in the last N seconds, where N is greater than or equal to 1 (5s is optional here). If the change amplitude of the coordinates of the center point of the eye area is less than or equal to the set threshold, execute the next step, otherwise return to re-obtain the video stream of the camera;

[0058] S2: Control the three-axis motion platform to move to a position at a first set distance (0.5 cm is optional here) from the patient, and then execute left and right movement instructions to obtain the optometry video stream;

[0059] S3: Process the optometry video stream frame by frame, identify the eye area, and crop it to retain only the eye area image to obtain an eye area image sequence, input the eye area image sequence into the classification network for recognition, and obtain the judgment results of forward movement, reverse movement, and neutralization;

[0060] S4: If the recognition result is neutral, the three-axis motion platform is controlled so that the retinoscope is close to the test person and the distance between it and the test person is less than the first set distance (0.5 cm is optionally selected here), and then it moves left and right to obtain the optometry video stream and execute the judgment process of step S3 again to obtain the first shadow motion result when close to the test person; the motor module for three-axis movement is controlled so that the retinoscope is away from the test person and the distance between it and the test person is greater than the first set distance (0.5 cm is optionally selected here), and then it moves left and right to obtain the optometry video stream and execute the judgment process of step S3 again to obtain the second shadow motion result when away from the test person. If the first shadow motion result is forward motion and the second shadow motion result is reverse motion, it is confirmed as the neutralization point, otherwise it is determined that it cannot be determined and the camera video stream is acquired again.

[0061] In this implementation, the classification network includes an Encoder-Decoder structure and an RNN structure. The Encoder-Decoder structure performs feature extraction and dimensionality reduction on the input eye area image sequence to obtain an eye image feature sequence, and then inputs the eye image feature sequence into the RNN for classification to obtain the shadow motion direction, wherein the RNN structure uses cross entropy loss for parameter update, and the Encoder-Decoder structure uses mean square error loss for parameter update.

[0062] In this implementation, the training is obtained by the following method: the image acquisition device described in Example 1 collects the optometry video of the human eye, and a professional doctor marks the direction of the shadow movement, and pre-processes the optometry video, which specifically includes the following steps:

[0063] Face recognition is performed frame by frame on the eye examination video, the eye area is identified and cropped to obtain an image sequence of the eye area, and then adaptive histogram equalization is performed on the eye area image sequence and noise is randomly added to obtain a preprocessed eye area image sequence. The preprocessed eye area image is used as input and the motion direction is used as a label to train a classification network.

[0064] Embodiment 2:

[0065] like Figure 6As shown, this implementation provides an image acquisition control system for retinoscopy, using the image acquisition device for retinoscopy described in Example 1 of the present invention, including:

[0066] The data acquisition unit is configured to: acquire the video stream of the camera, perform face recognition on the video stream frame by frame, identify the eye area, and record the coordinates of the center point of the eye area frame by frame, and compare the coordinates of the center point of the eye area in the last N seconds, where N is greater than or equal to 1. If the change amplitude of the coordinates of the center point of the eye area is less than or equal to a set threshold, execute the process of the optometry control unit, otherwise return to re-acquire the video stream of the camera;

[0067] The optometry control unit is configured to: control the three-axis motion platform, move the retinoscope to a position at a first set distance from the patient, and then execute left and right movement instructions to obtain an optometry video stream;

[0068] The shadow motion judgment unit is configured to: process the optometry video stream frame by frame, identify the eye area, and crop it to retain only the eye area image to obtain an eye area image sequence, input the eye area image sequence into the classification network for recognition, and obtain the judgment results of forward motion, reverse motion, and neutralization;

[0069] The neutralization judgment unit is configured as follows: if the recognition result is neutralization, the three-axis motion platform is controlled so that the retinoscope is close to the tester and the distance between the retinoscope and the tester is less than a first set distance, and then the left and right movements are performed to obtain the optometry video stream and the judgment process of the shadow motion judgment unit is performed again to obtain the first shadow motion result when close to the tester; the motor module for three-axis movement is controlled so that the retinoscope is away from the tester and the distance between the retinoscope and the tester is greater than a first set distance, and then the left and right movements are performed to obtain the optometry video stream and the judgment process of the shadow motion judgment unit is performed again to obtain the second shadow motion result when away from the tester. If the first shadow motion result is a forward motion and the second shadow motion result is a reverse motion, it is confirmed as a neutralization point, otherwise it is determined that it cannot be determined and the camera video stream acquisition is performed again.

[0070] It is understandable that the above-mentioned modules can be separately or completely combined into one or several other units to constitute, or one (some) of the units can be further divided into multiple smaller units in function to constitute, which can achieve the same operation without affecting the realization of the technical effects of the embodiments of the present application. The above-mentioned units are divided based on logical functions. In practical applications, the function of one unit can also be implemented by multiple units, or the functions of multiple units can be implemented by one unit. In other embodiments of the present application, the image processing device may also include other units. In practical applications, these functions can also be implemented with the assistance of other units, and can be implemented by the collaboration of multiple units.

[0071] According to another embodiment of the present application, the system described in this embodiment can be constructed and the image processing method of the embodiment of the present application can be implemented by running a computer program (including program code) capable of executing the steps involved in the corresponding method described in Example 1 on a general computing device such as a computer including processing elements and storage elements such as a central processing unit (CPU)-random access memory (RAM)-read-only memory (ROM). The computer program can be recorded on, for example, a computer-readable recording medium, and loaded into the above-mentioned computing device through the computer-readable recording medium and run therein.

[0072] Embodiment 3:

[0073] like Figure 7 As shown, Embodiment 4 of the present invention provides an electronic device, which includes a processor 1001, a communication interface 1002, and a computer-readable storage medium 1003. The processor 1001, the communication interface 1002, and the computer-readable storage medium 1003 may be connected via a bus or other means.

[0074] Among them, the communication interface 1002 is used to receive and send data, the computer-readable storage medium 1003 can be stored in the memory of the electronic device, the computer-readable storage medium 1003 is used to store a computer program, the computer program includes program instructions, and the processor 1001 is used to execute the program instructions stored in the computer-readable storage medium 1003.

[0075] Processor 1001 (or CPU (Central Processing Unit)) is the computing core and control core of the electronic device, which is suitable for implementing one or more instructions, specifically suitable for loading and executing one or more instructions to implement corresponding method processes or corresponding functions.

[0076] The processor 1001 is configured to execute the following process:

[0077] Get the video stream of the camera, perform face recognition on the video stream frame by frame, identify the eye area, and record the coordinates of the center point of the eye area frame by frame. Compare the coordinates of the center point of the eye area in the last N seconds, where N is greater than or equal to 1 (5s is optional here). If the change amplitude of the coordinates of the center point of the eye area is less than or equal to the set threshold, execute the next step, otherwise return to the previous step to re-acquire the video stream of the camera;

[0078] Control the three-axis motion platform to move to a position at a first set distance from the patient (0.5 cm is optional here), and then execute left and right movement instructions to obtain the optometry video stream;

[0079] The optometry video stream is processed frame by frame, the eye area is identified, and then cropped to retain only the eye area image to obtain the eye area image sequence, which is then input into the classification network for identification to obtain the forward motion, reverse motion, and neutralization judgment results;

[0080] If the recognition result is neutral, the three-axis motion platform is controlled so that the retinoscope is close to the test person and the distance between it and the test person is less than the first set distance (0.5 cm is optionally selected here), and then it is moved left and right to obtain the optometry video stream and the judgment process of step S3 is executed again to obtain the first shadow motion result when close to the test person; the motor module for three-axis movement is controlled so that the retinoscope is away from the test person and the distance between it and the test person is greater than the first set distance (0.5 cm is optionally selected here), and then it is moved left and right to obtain the optometry video stream and the judgment process of step S3 is executed again to obtain the second shadow motion result when away from the test person. If the first shadow motion result is forward motion and the second shadow motion result is reverse motion, it is confirmed as the neutral point, otherwise it is determined that it cannot be determined and the camera video stream acquisition is performed again.

[0081] Embodiment 4:

[0082] This embodiment provides a computer-readable storage medium (Memory), which is a memory device in an electronic device for storing programs and data. It is understandable that the computer-readable storage medium here can include both built-in storage media in the electronic device and, of course, extended storage media supported by the electronic device. The computer-readable storage medium provides a storage space that stores the processing system of the electronic device.

[0083] In addition, the storage space also stores one or more instructions suitable for being loaded and executed by the processor. These instructions may be one or more computer programs (including program codes). It should be noted that the computer-readable storage medium here may be a high-speed RAM memory or a non-volatile memory ( memory), such as at least one disk memory; optionally, it can also be at least one computer-readable storage medium located away from the aforementioned processor.

[0084] In one embodiment, the computer-readable storage medium stores one or more instructions; the processor loads and executes the one or more instructions stored in the computer-readable storage medium to implement the following process:

[0085] Get the video stream of the camera, perform face recognition on the video stream frame by frame, identify the eye area, and record the coordinates of the center point of the eye area frame by frame. Compare the coordinates of the center point of the eye area in the last N seconds, where N is greater than or equal to 1 (5s is optional here). If the change amplitude of the coordinates of the center point of the eye area is less than or equal to the set threshold, execute the next step, otherwise return to the previous step to re-acquire the video stream of the camera;

[0086] Control the three-axis motion platform to move to a position at a first set distance from the patient (0.5 cm is optional here), and then execute left and right movement instructions to obtain the optometry video stream;

[0087] The optometry video stream is processed frame by frame, the eye area is identified, and then cropped to retain only the eye area image to obtain the eye area image sequence, which is then input into the classification network for identification to obtain the forward motion, reverse motion, and neutralization judgment results;

[0088] If the recognition result is neutral, the three-axis motion platform is controlled so that the retinoscope is close to the test person and the distance between it and the test person is less than the first set distance (0.5 cm is optionally selected here), and then it is moved left and right to obtain the optometry video stream and the judgment process of step S3 is executed again to obtain the first shadow motion result when close to the test person; the motor module for three-axis movement is controlled so that the retinoscope is away from the test person and the distance between it and the test person is greater than the first set distance (0.5 cm is optionally selected here), and then it is moved left and right to obtain the optometry video stream and the judgment process of step S3 is executed again to obtain the second shadow motion result when away from the test person. If the first shadow motion result is forward motion and the second shadow motion result is reverse motion, it is confirmed as the neutral point, otherwise it is determined that it cannot be determined and the camera video stream acquisition is performed again.

[0089] Embodiment 5:

[0090] This embodiment provides a computer program product or a computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of an electronic device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the electronic device performs the following process:

[0091] Get the video stream of the camera, perform face recognition on the video stream frame by frame, identify the eye area, and record the coordinates of the center point of the eye area frame by frame. Compare the coordinates of the center point of the eye area in the last N seconds, where N is greater than or equal to 1 (5s is optional here). If the change amplitude of the coordinates of the center point of the eye area is less than or equal to the set threshold, execute the next step, otherwise return to the previous step to re-acquire the video stream of the camera;

[0092] Control the three-axis motion platform to move to a position at a first set distance from the patient (0.5 cm is optional here), and then execute left and right movement instructions to obtain the optometry video stream;

[0093] The optometry video stream is processed frame by frame, the eye area is identified, and then cropped to retain only the eye area image to obtain the eye area image sequence, which is then input into the classification network for identification to obtain the forward motion, reverse motion, and neutralization judgment results;

[0094] If the recognition result is neutral, the three-axis motion platform is controlled so that the retinoscope is close to the test person and the distance between it and the test person is less than the first set distance (0.5 cm is optionally selected here), and then it is moved left and right to obtain the optometry video stream and the judgment process of step S3 is executed again to obtain the first shadow motion result when close to the test person; the motor module for three-axis movement is controlled so that the retinoscope is away from the test person and the distance between it and the test person is greater than the first set distance (0.5 cm is optionally selected here), and then it is moved left and right to obtain the optometry video stream and the judgment process of step S3 is executed again to obtain the second shadow motion result when away from the test person. If the first shadow motion result is forward motion and the second shadow motion result is reverse motion, it is confirmed as the neutral point, otherwise it is determined that it cannot be determined and the camera video stream acquisition is performed again.

[0095] A person skilled in the art can appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in this application 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. A person skilled in the art 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.

[0096] In the above embodiments, it can be implemented in whole or in part by software-hardware-firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on the computer, the process or function according to the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer-special-purpose computer-computer network-or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted by a computer-readable storage medium. The computer instructions can be transmitted from a website site-computer-server or data center to another website site-computer-server or data center by wired (for example, coaxial cable-optical fiber-digital line (DSL)) or wireless (for example, infrared-wireless-microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data processing device such as a server-data center that contains one or more available media integration. The available medium can be a magnetic medium (for example, a floppy disk-hard disk-tape)-optical medium (for example, DVD)-or a semiconductor medium (for example, a solid-state hard disk (SSD)) and the like.

[0097] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An image acquisition device for retinoscopy, characterized in that: include: A fixing assembly, a retinoscope, a camera, a three-axis motion platform and a base, wherein the fixing assembly comprises a retinoscope fixing seat and a camera fixing seat connected by a connecting piece; The retinoscope is connected to the retinoscope fixing seat, the camera is connected to the camera fixing seat, the camera fixing seat is connected to the retinoscope fixing seat through a connecting piece, the camera is located behind the retinoscope and the camera is facing the retinoscope observation hole; The fixing component is connected to the three-axis motion platform and can move in three directions driven by the three-axis motion platform. The three-axis motion platform is connected to the base, and a forehead support fixer is connected to the base.

2. The image acquisition device for retinoscopy according to claim 1, characterized in that: The motor module of the three-axis motion platform is fixed on the base, the motor module is connected to the motor controller, the motor controller is fixed on the base, and the motor controller, the camera and the retinoscope are respectively connected to the computer terminal.

3. The image acquisition device for retinoscopy according to claim 1, characterized in that: The base comprises a bottom plate and a base shell, the bottom plate and the base shell are connected, and the bottom plate is connected to the forehead support fixer.

4. A method for controlling image acquisition of retinoscopy, characterized in that: Using the image acquisition device for retinoscopy according to any one of claims 1 to 3, The process includes: Get the video stream of the camera, perform face recognition on the video stream frame by frame, identify the eye area, and record the coordinates of the center point of the eye area frame by frame. Compare the coordinates of the center point of the eye area in the last N seconds, where N is greater than or equal to 1. If the change in the coordinates of the center point of the eye area is less than or equal to the set threshold, execute the next step, otherwise return to re-acquire the video stream of the camera; Control the three-axis motion platform to move the retinoscope to a position at a first set distance from the patient, and then execute left and right movement instructions to obtain the optometry video stream; The optometry video stream is processed frame by frame, the eye area is identified, and then cropped to retain only the eye area image to obtain the eye area image sequence, which is then input into the classification network for identification to obtain the forward-reverse and neutralization judgment results; If the recognition result is neutral, the three-axis motion platform is controlled so that the retinoscope is close to the test person and the distance between it and the test person is less than the first set distance, and then it moves left and right to obtain the optometry video stream and execute the previous judgment process again to obtain the first shadow motion result when close to the test person; the motor module for three-axis movement is controlled so that the retinoscope is away from the test person and the distance between it and the test person is greater than the first set distance, and then it moves left and right to obtain the optometry video stream and execute the previous judgment process again to obtain the second shadow motion result when away from the test person. If the first shadow motion result is forward motion and the second shadow motion result is reverse motion, it is confirmed as the neutral point, otherwise it is determined that it cannot be determined and the camera video stream is acquired again.

5. The image acquisition control method for retinoscopy according to claim 4, characterized in that: The Encoder-Decoder structure is used to extract features and reduce the dimension of the input eye area image sequence to obtain the eye image feature sequence, which is then input into the RNN for classification to obtain the forward-reverse and neutralization judgment results.

6. An image acquisition and control system for retinoscopy, characterized in that: Using the image acquisition device for retinoscopy according to any one of claims 1 to 3, The process includes: The data acquisition unit is configured to: acquire the video stream of the camera, perform face recognition on the video stream frame by frame, identify the eye area, and record the coordinates of the center point of the eye area frame by frame, and compare the coordinates of the center point of the eye area in the last N seconds, where N is greater than or equal to 1. If the change amplitude of the coordinates of the center point of the eye area is less than or equal to a set threshold, execute the process of the optometry control unit, otherwise return to re-acquire the video stream of the camera; The optometry control unit is configured to: control the three-axis motion platform, move the retinoscope to a position at a first set distance from the patient, and then execute left and right movement instructions to obtain an optometry video stream; The shadow motion judgment unit is configured to: process the optometry video stream frame by frame, identify the eye area, and crop it to retain only the eye area image to obtain an eye area image sequence, input the eye area image sequence into the classification network for recognition, and obtain the forward motion-reverse motion and neutralization judgment results; The neutralization judgment unit is configured as follows: if the recognition result is neutralization, the three-axis motion platform is controlled so that the retinoscope is close to the tester and the distance between the retinoscope and the tester is less than a first set distance, and then the left and right movements are performed to obtain the optometry video stream and the judgment process of the shadow motion judgment unit is performed again to obtain the first shadow motion result when close to the tester; the motor module for three-axis movement is controlled so that the retinoscope is away from the tester and the distance between the retinoscope and the tester is greater than a first set distance, and then the left and right movements are performed to obtain the optometry video stream and the judgment process of the shadow motion judgment unit is performed again to obtain the second shadow motion result when away from the tester. If the first shadow motion result is a forward motion and the second shadow motion result is a reverse motion, it is confirmed as a neutralization point, otherwise it is determined that it cannot be determined and the camera video stream acquisition is performed again.

7. The image acquisition and control system for retinoscopy according to claim 6, characterized in that: In the shadow motion judgment unit, the Encoder-Decoder structure is used to extract features and reduce the dimension of the input eye area image sequence to obtain the eye image feature sequence, which is then input into the RNN for classification to obtain the forward motion, reverse motion and neutralization judgment results.

8. A computer terminal, characterized in that: include: a processor and a computer readable storage medium; a processor adapted to execute a computer program; A computer-readable storage medium, wherein a computer program is stored in the computer-readable storage medium, and when the computer program is executed by the processor, the image acquisition control method for retinoscopy according to claim 4 or 5 is implemented.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and the computer program is suitable for being loaded by a processor and executing the image acquisition control method for retinoscopy according to claim 4 or 5.

10. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the image acquisition control method for retinoscopy according to claim 4 or 5 is implemented.

Images