An ADHD assessment system based on eye movements

Abstract

The invention relates to the technical field of attention assessment, and in particular to an ADHD assessment system based on eye movement, comprising an image acquisition module for collecting nine-position eye movement pictures, an intelligent picture screening module for screening qualified eye position pictures, an image processing module for intelligently cutting and adjusting the qualified eye position pictures, a result output module and a printing module. The invention uses the image acquisition module, the intelligent picture screening module, the picture processing module and the result output module to cooperate to collect nine-position eye movement pictures to assess the attention of a subject, and the assessment is performed by monitoring the movement trajectory and fixation point of the eyes. The assessment does not cause any physical discomfort or inconvenience to the subject, has no requirements for the subject, and does not feel oppressive. The eye movement assessment can automatically analyze and record data through computer software, is relatively more efficient and repeatable, and improves the efficiency of attention assessment.

Description

Technical Field

[0001] The invention belongs to the technical field of attention assessment, and in particular relates to an ADHD assessment system based on eye movement. Background Art

[0002] ADHD is the abbreviation of Attention Deficit Hyperactivity Disorder. It is a common neurodevelopmental disorder characterized by long-term inattention, hyperactivity, and impulsive behavior. ADHD usually begins to appear in childhood, but may continue into adulthood. ADHD can have a negative impact on an individual's learning, work, and social abilities. Therefore, children should be evaluated for ADHD for non-therapeutic purposes during childhood. Early detection and appropriate treatment methods, such as behavioral therapy, psychoeducation, and medication, can help individuals manage symptoms and improve their quality of life.

[0003] After searching, the Chinese patent document application number is 202111429477.8, which discloses an attention assessment method and system. Based on a smart mobile device, the user is tested for a game to determine the subject's attention duration and impulse control data; the attention variables are used to fit the attention duration and impulse control data to remove the interference introduced by the game test; at least the attention duration and impulse control data after the interference is removed are used to assist the physician in the attention assessment. This embodiment of the invention avoids the hardware requirements for the environment in the attention assessment, and at the same time removes the interference introduced into the test results due to environmental changes, realizing the popularization of offline attention assessment; at the same time, interesting tests are used to enhance the completion willingness of the tested individual, allowing users to persist and ensure the accuracy of attention assessment when the environment changes.

[0004] However, the above-mentioned attention assessment needs to be conducted in the form of games, and the test subjects need to perform tasks, fill out questionnaires, etc., which will have certain requirements and pressure on the test subjects, making the accuracy of the test results less accurate. It also requires more time and manual analysis, which is slightly time-consuming and reduces the efficiency of ADHD assessment. Therefore, we need to propose an ADHD assessment system based on eye movements to solve the above-mentioned problems. Summary of the invention

[0005] In view of the above problems, the present invention provides an ADHD assessment system based on eye movement, comprising an image acquisition module for collecting nine-position eye movement pictures, an intelligent picture screening module for screening qualified eye position photos, an image processing module for intelligently cutting and adjusting qualified eye position photos, a result output module for analyzing and evaluating the processed eye position photos, and a printing module for printing photos and reports on site, wherein the image acquisition module is electrically connected to the intelligent picture screening module, the intelligent picture screening module is electrically connected to the picture processing module, the picture processing module is electrically connected to the result output module, and the result output module is electrically connected to the printing module;

[0006] The qualified eye position photos screened by the intelligent image screening module are judged as follows: the eyes are open, the corneal light reflection point is exposed, and the image is symmetrical in the sagittal plane. If any of the following conditions is present: the eyes are not open, the corneal light reflection point is not exposed, and the image is asymmetrical in the sagittal plane, the photo is judged as unqualified eye position photo, and the unqualified eye position photos and qualified eye position photos are classified and transmitted to the image processing module for processing;

[0007] The image processing module deletes the unqualified eye position photos in which the eyes are not opened and the corneal light reflection point is not exposed, and performs horizontal adjustment on the eye position photos with asymmetric sagittal plane of the image to make the inner and outer parts of the eyes The angle is adjusted to a horizontal position. If the horizontal position adjustment is successful, it will be processed as a qualified eye position photo. If the horizontal position adjustment is unsuccessful, the unqualified eye position photo will be deleted and the person being tested will be prompted to retake the photo. The qualified eye position photo will be cut according to the standard ratio of 5:2 for a single photo. The horizontal position will be determined first, and then the vertical position will be determined in the same proportion to make the eye position vertically centered, and then the nine-direction eye movement picture will be automatically generated;

[0008] When evaluating attention, the result output module divides the eye movement pictures within a period of time into time slices, and then analyzes the eye movement pictures in each time slice to observe the eye dwell time in different directions and the smoothness of the eye movement. If the eye dwell time is relatively long and the eye movement is smooth, it is determined that the direction has attracted attention.

[0009] Furthermore, the image acquisition module includes an eye tracker, a display and a computer. The computer is internally provided with image acquisition software for real-time acquisition and recording of eye movement pictures. The computer is connected to the eye tracker and the display respectively.

[0010] Furthermore, the eye tracker includes an infrared camera for capturing eye position and movement, a laser transmitter for providing eye reflection signals, a data processor for receiving and processing eye movement data, and a wireless transceiver for transmitting the processed data to a computer, wherein the laser transmitter is connected to one end of the infrared camera, the other end of the infrared camera is electrically connected to one end of the data processor, the other end of the data processor is electrically connected to one end of the wireless transceiver, and the other end of the wireless transceiver is connected to the computer.

[0011] Furthermore, the intelligent image screening module includes an image receiver for receiving eye position photos, an image processor for performing image processing on the eye position photos, and a processor for detecting the height and width of the palpebral fissure and the external A feature extractor for measuring the hairline distance on both sides of the angular distance, an evaluator for judging whether an eye position photo is qualified, and a sifter for screening and classifying the eye position photos, wherein the image receiver is connected to one end of the image processor, the other end of the image processor is connected to one end of the feature extractor, the other end of the feature extractor is connected to one end of the evaluator, and the other end of the evaluator is connected to one end of the sifter.

[0012] Furthermore, the image processing module includes an unqualified eye position determiner for determining whether an eye position photo is qualified, a horizontal adjuster, a locator for locating the eye position, a cropper and a nine-direction eye movement image generator, one end of the unqualified eye position determiner is electrically connected to one end of the horizontal adjuster, the other end of the horizontal adjuster and the other end of the feature extractor are both connected to one end of the locator, the other end of the locator is connected to one end of the cropper, and the other end of the cropper is connected to one end of the nine-direction eye movement image generator.

[0013] Furthermore, the unqualified eye position determiner determines whether the eye position photo is qualified according to a specific rule or algorithm, and deletes the photo if the eye position photo is unqualified.

[0014] Furthermore, the horizontal adjuster performs horizontal adjustment on the eye position photograph with asymmetric sagittal plane of the image, so that the inner and outer canthus angles are adjusted to a horizontal position.

[0015] Furthermore, the cropper cuts the qualified eye position photo into a single photo at a ratio of 5:2 according to the set standard ratio, first positions it horizontally, and then positions it vertically in equal proportion to make the eye position vertically centered.

[0016] Furthermore, the result output module uses computer vision algorithms and machine learning techniques to analyze the processed eye position photos, and then evaluates the eye position photos based on the output of the analysis results through set rules, thresholds or models, and then outputs the results to a suitable interface, and then displays the attention evaluation results in a graphical manner on a visualization interface.

[0017] Furthermore, the printing module includes an inkjet head for spraying pigment on a printing medium to form an image, an ink cartridge for providing ink to the inkjet head, a printing medium feeding device for guiding the printing medium for printing, a control circuit responsible for controlling the printing process, and a transmission system responsible for controlling and managing the movement between the inkjet head and the printing medium feeding device.

[0018] The beneficial effects of the present invention are:

[0019] 1. The present invention cooperates with an image acquisition module, an intelligent picture screening module, a picture processing module and a result output module to collect nine-direction eye movement pictures to evaluate the attention of the testee. This is done by monitoring the movement trajectory and gaze point of the eyes. There is no physical discomfort or inconvenience for the testee, no requirements for the testee, and the testee does not feel oppressed. The eye movement evaluation can automatically analyze and record data through computer software, which is relatively more efficient and repeatable, thereby improving the efficiency of attention evaluation.

[0020] 2. The present invention facilitates the classification and transmission of unqualified eye position photos and qualified eye position photos to the image processing module for processing through the setting of the intelligent image screening module.

[0021] 3. The present invention facilitates intelligent attention assessment and analysis based on nine-position eye position photos through the setting of the result output module, without the need for manual analysis, thereby improving the efficiency of attention assessment to a certain extent.

[0022] 4. The present invention prints photos and reports to the test subjects on site through the setting of the printing module, so that the test subjects can obtain the visual presentation of the test results in time and understand their test scores or evaluation results.

[0023] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures pointed out in the description, claims and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0025] Figure 1 A system block diagram according to an embodiment of the present invention is shown;

[0026] Figure 2 A schematic diagram of a process according to an embodiment of the present invention is shown;

[0027] Figure 3 A system block diagram of a picture acquisition module according to an embodiment of the present invention is shown;

[0028] Figure 4 A system block diagram of an intelligent picture screening module according to an embodiment of the present invention is shown;

[0029] Figure 5 A circuit diagram of a failed eye position determiner according to an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0030] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0031] The embodiment of the present invention provides an ADHD assessment system based on eye movement, such as Figure 1 As shown, it includes an image acquisition module for acquiring nine-position eye movement pictures, an intelligent picture screening module for screening qualified eye position photos, an image processing module for intelligently cutting and adjusting qualified eye position photos, a result output module for analyzing and evaluating the processed eye position photos, and a printing module for printing photos and reports on site, the image acquisition module is electrically connected to the intelligent picture screening module, the intelligent picture screening module is electrically connected to the picture processing module, the picture processing module is electrically connected to the result output module, and the result output module is electrically connected to the printing module.

[0032] like Figure 3As shown, the image acquisition module includes an eye tracker, a display and a computer. The computer is internally provided with image acquisition software for real-time acquisition and recording of eye movement pictures. The computer is connected to the eye tracker and the display respectively. The eye tracker acquires eye movement pictures of the tester in nine directions, namely, front, top, upper left, left, lower left, bottom, lower right, right and upper right. At the same time, the eye tracker can measure the information of the position, fixation point and movement trajectory of the eyeball. The eye tracker is embedded in the display. The display is used to present visual stimuli for the testee to participate in the eye movement task, such as text, image or video. The display has high resolution, low latency and appropriate refresh rate to ensure accurate acquisition of the eye tracker. The computer can be a desktop computer, a laptop or a specially configured mobile device.

[0033] The eye tracker includes an infrared camera for capturing eye position and movement, a laser transmitter for providing eye reflection signals, a data processor for receiving and processing eye movement data, and a wireless transceiver for transmitting the processed data to a computer. The laser transmitter is connected to one end of the infrared camera, the other end of the infrared camera is electrically connected to one end of the data processor, the other end of the data processor is electrically connected to one end of the wireless transceiver, and the other end of the wireless transceiver is connected to the computer.

[0034] When collecting data, the eye tracker emits infrared light through a laser transmitter. When the light emitted by the laser transmitter is received by the eyeball, the eyeball will reflect the received light to the infrared camera. The infrared camera determines the position and movement of the eyeball based on the corneal reflection to capture pictures of the eyeball movement, and converts the picture data into digital signals to transmit to the computer.

[0035] The criteria for determining qualified eye position photos screened by the intelligent image screening module are: eyes are open, corneal light reflection points are exposed, and the image is sagittal symmetrical. If any of the following conditions is present: eyes are not open, corneal light reflection points are not exposed, and the image is sagittal asymmetric, the photo is judged to be unqualified eye position photo, and the unqualified eye position photos and qualified eye position photos are classified and transmitted to the image processing module for processing.

[0036] like Figure 4 As shown, the intelligent picture screening module includes an image receiver for receiving eye position photos, an image processor for performing image processing on the eye position photos, and an image processor for detecting the height and width of the palpebral fissure and the external A feature extractor for the distance between the eye angle and the hairline on both sides, an evaluator for judging whether the eye position photo is qualified, and a sifter for screening and classifying the eye position photos, the image receiver is connected to one end of the image processor, the other end of the image processor is connected to one end of the feature extractor, the other end of the feature extractor is connected to one end of the evaluator, and the other end of the evaluator is connected to one end of the sifter, the eye position photo is received by the image receiver, which can be an image file reading, a real-time input of a webcam or an image sensor, and the image data is passed to the image processor, and the image is preprocessed by the image processor. Preprocessing includes image denoising, image enhancement, edge detection, etc., which are used to improve image quality and optimize image features for subsequent analysis. The preprocessed image will be passed to the feature extractor, which is a component for extracting key features from the eye position photo. For the eye position photo, the features to be extracted include the height and width of the palpebral fissure and the distance between the outer canthus angle and the hairline on both sides.

[0037] The feature extractor uses traditional computer vision methods (such as SIFT, HOG, etc.) or deep learning-based convolutional neural networks (CNN) to extract these features, and determines whether the eyes are open by detecting the ratio of the palpebral fissure height to the palpebral fissure width. The distance from the hairline on both sides of the angle is used to determine whether the sagittal plane of the image is symmetrical. The evaluator is used to determine whether the eye position photo is qualified based on the image extracted by the feature extractor. By analyzing the features extracted by the feature extractor, the quality and qualification of the eye position photo are detected. The evaluator includes various algorithms and rules for evaluating the accuracy, clarity, focus, occlusion and other factors of the eye position photo. The screener screens the eye position photo based on the evaluation results given by the evaluator and the pre-set screening criteria to determine whether it is qualified. The screener can be based on simple rules of thresholds, or it can use machine learning or deep learning classification models to make judgments.

[0038] The image processing module deletes the unqualified eye position photos in which the eyes are not opened and the corneal light reflection point is not exposed, and performs horizontal adjustment on the eye position photos with asymmetric sagittal plane of the image to make the inner and outer parts of the eyes The angle is adjusted to a horizontal position. If the horizontal position adjustment is successful, it will be processed as a qualified eye position photo. If the horizontal position adjustment is unsuccessful, the unqualified eye position photo will be deleted and the person being tested will be prompted to retake the photo. The qualified eye position photo will be cut according to the standard ratio of 5:2 for a single photo. The horizontal position is determined first, and the vertical position is determined in equal proportion to make the eye position vertically centered. Then the nine-direction eye movement picture will be automatically generated.

[0039] The image processing module includes an unqualified eye position determiner for determining whether an eye position photo is qualified, a horizontal adjuster, a locator for locating the eye position, a cropper, and a nine-position eye movement picture generator. One end of the unqualified eye position determiner is electrically connected to one end of the horizontal adjuster, the other end of the horizontal adjuster and the other end of the feature extractor are both connected to one end of the locator, the other end of the locator is connected to one end of the cropper, and the other end of the cropper is connected to one end of the nine-position eye movement picture generator. The unqualified eye position determiner determines whether the eye position photo is qualified according to specific rules or algorithms, for example, whether the eyes are not open, whether the corneal light reflection point is exposed, etc. If the eye position photo is unqualified, the photo is deleted; the horizontal adjuster performs horizontal adjustment for the eye position photo with asymmetric sagittal plane of the image, so that the inner and outer canthus angles are adjusted to a horizontal position. Image processing technology can be used, such as image rotation, affine transformation, etc.; the locator is used to locate the position of the eye and determine the horizontal position of the eye for horizontal adjustment and cropping. Methods such as feature point detection and template matching can be used; the cropper cuts qualified eye position photos into a single 5:2 ratio according to the set standard ratio. First, horizontal positioning is performed, and then the vertical positioning is proportional to make the eye position vertically centered; the nine-direction eye movement image generator automatically generates nine-direction eye movement images based on the cropped eye images, and image synthesis, transformation and other operations can be performed through image processing technology.

[0040] like Figure 5 As shown, the unqualified eye position determiner includes a chip U1 and a chip U2, wherein the second pin and the sixth pin of the chip U1 are connected to the third pin of the chip U2, and the second pin and the sixth pin of the chip U2 are connected to the connecting end of the second pin and the sixth pin of the chip U1 through a resistor R6, and one pin of the chip U2 is connected to a capacitor C1, and the connecting end of the resistor R6 and the chip U1 is connected to a resistor R2, and one end of the resistor R2 is connected to a transistor Q1 having one end receiving an input signal, and the base of the transistor Q1 is connected to the resistor R1, and one end of the resistor R1 is connected to a resistor R5, and the connecting end of the resistor R5 and the resistor R1 is connected to the three pins of the chip U1, and a resistor R is connected in parallel between the other end of the resistor R5 and the emitter of the transistor Q1 3. Transistor Q2, resistor R4 and transistor Q3. The eight pins of the chip U2 are connected to resistor R7. One end of the resistor R7 is connected to a diode D1. One end of the diode D1 is connected to a relay K1. One end of the relay K1 is connected to a 12V power supply. One end of the power supply is connected to the other end of the resistor R7. The other end of the relay K1 is provided with a data output port, and one end of the data output port is connected to one pin of the chip U1 and one pin of the chip U2. Chip U1 and chip U2 have built-in computer vision algorithms, such as Haar features, SIFT, SURF and HOG to extract eye features, and use eye features to help determine whether the eyes are open, the position of the corneal light spot, etc.

[0041] The result output module uses computer vision algorithms and machine learning techniques to analyze the processed eye position photos, and then evaluates the eye position photos according to the output of the analysis results through the set rules, thresholds or models, and then outputs the results to a suitable interface so that users or other systems can obtain the results, and then displays the attention evaluation results in a graphical manner on the visualization interface. When evaluating attention, the eye movement pictures within a period of time are divided into time slices, for example, each second is divided into multiple time slices. Then, the eye movement pictures in each time slice are analyzed to observe the eye's residence time in different directions and the smoothness of the eye movement. If the eye's residence time is relatively long and the eye movement is smooth, it is determined that the direction has attracted attention;

[0042] The present invention also provides another judgment method: the nine directions are analyzed according to the position of the eyeballs, and it is observed which direction has a concentrated stay and a longer duration. If the eyeballs stay near a certain direction and the stay time in other directions is shorter, it is determined that this direction has attracted attention. No manual analysis is required, which improves the efficiency of attention assessment to a certain extent.

[0043] The printing module includes an inkjet head for spraying pigment on a printing medium to form an image, an ink cartridge for providing ink for the inkjet head, a printing medium feed device for guiding the printing medium for printing, a control circuit responsible for controlling the printing process, and a transmission system responsible for controlling and managing the movement between the inkjet head and the printing medium feed device. During printing, the ink is sprayed microscopically onto the printing medium by the inkjet head. The printing medium is paper or other film materials capable of carrying an image. The inkjet position and the ink spray amount of the inkjet head are controlled to form an image or text. After receiving the data to be printed, the printing control circuit controls the inkjet position and the ink spray amount of the inkjet head according to the image content, so as to construct an image line by line and point by point on the printing medium, and prints the photos and reports to the test subject on site, so as to facilitate the test subject to obtain a visual presentation of the test results in a timely manner, so that the test subject can understand their test scores or evaluation results.

[0044] like Figure 2As shown, when in use, nine-position eye movement pictures are first collected through the image acquisition module, and then the collected eye movement pictures are intelligently screened for qualified eye position photos and unqualified eye position photos through the intelligent picture screening module, and horizontal adjustment processing is performed on the pictures with sagittal asymmetry in the unqualified eye position photos. After qualified adjustment, the pictures are cropped together with the qualified eye position photos, and then nine-position eye movement pictures are generated. Finally, attention assessment is performed based on the nine-position eye movement pictures, and pictures of unopened eyes and unexposed corneal light reflection points in the unqualified eye position photos and unqualified pictures of horizontal adjustment of sagittal asymmetry pictures are deleted. The method is performed by monitoring the movement trajectory and gaze point of the eyes, without any physical discomfort or inconvenience to the testee, without any requirements for the testee, and the testee does not feel oppressed. The eye movement assessment can automatically analyze and record data through computer software, which is relatively more efficient and repeatable, thereby improving the efficiency of attention assessment.

[0045] Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent substitutions for some of the technical features therein; and these modifications or substitutions do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An ADHD assessment system based on eye movement, characterized by: It includes an image acquisition module for acquiring nine-position eye movement pictures, an intelligent picture screening module for screening qualified eye position pictures, an image processing module for intelligently cutting and adjusting qualified eye position pictures, a result output module for analyzing and evaluating the processed eye position pictures, and a printing module for printing the pictures and reports on site, wherein the image acquisition module is electrically connected to the intelligent picture screening module, the intelligent picture screening module is electrically connected to the picture processing module, the picture processing module is electrically connected to the result output module, and the result output module is electrically connected to the printing module; The qualified eye position photos screened by the intelligent image screening module are judged as follows: the eyes are open, the corneal light reflection point is exposed, and the image is symmetrical in the sagittal plane. If any of the following conditions is present: the eyes are not open, the corneal light reflection point is not exposed, and the image is asymmetrical in the sagittal plane, the photo is judged as unqualified eye position photo, and the unqualified eye position photos and qualified eye position photos are classified and transmitted to the image processing module for processing; The image processing module deletes the unqualified eye position photos in which the eyes are not opened and the corneal light reflection point is not exposed, and performs horizontal adjustment on the eye position photos with asymmetric sagittal plane of the image to make the inner and outer parts of the eyes The angle is adjusted to a horizontal position. If the horizontal position adjustment is successful, it will be processed as a qualified eye position photo. If the horizontal position adjustment is unsuccessful, the unqualified eye position photo will be deleted and the person being tested will be prompted to retake the photo. The qualified eye position photo will be cut according to the standard ratio of 5:2 for a single photo. The horizontal position will be determined first, and then the vertical position will be determined in the same proportion to make the eye position vertically centered, and then the nine-direction eye movement picture will be automatically generated; When evaluating attention, the result output module divides the eye movement pictures within a period of time into time slices, and then analyzes the eye movement pictures in each time slice to observe the eye dwell time in different directions and the smoothness of the eye movement. If the eye dwell time is relatively long and the eye movement is smooth, it is determined that the direction has attracted attention.

2. The ADHD assessment system based on eye movement according to claim 1, characterized in that: The image acquisition module includes an eye tracker, a display and a computer. The computer is internally provided with image acquisition software for real-time acquisition and recording of eye movement pictures. The computer is connected to the eye tracker and the display respectively.

3. The ADHD assessment system based on eye movement according to claim 2, characterized in that: The eye tracker includes an infrared camera for capturing eye position and movement, a laser transmitter for providing eye reflection signals, a data processor for receiving and processing eye movement data, and a wireless transceiver for transmitting the processed data to a computer. The laser transmitter is connected to one end of the infrared camera, the other end of the infrared camera is electrically connected to one end of the data processor, the other end of the data processor is electrically connected to one end of the wireless transceiver, and the other end of the wireless transceiver is connected to the computer.

4. The ADHD assessment system based on eye movement according to claim 3, characterized in that: The intelligent picture screening module includes an image receiver for receiving eye position photos, an image processor for performing image processing on the eye position photos, and a processor for detecting the height and width of the palpebral fissure and the external A feature extractor for measuring the hairline distance on both sides of the angular distance, an evaluator for judging whether an eye position photo is qualified, and a sifter for screening and classifying the eye position photos, wherein the image receiver is connected to one end of the image processor, the other end of the image processor is connected to one end of the feature extractor, the other end of the feature extractor is connected to one end of the evaluator, and the other end of the evaluator is connected to one end of the sifter.

5. The ADHD assessment system based on eye movement according to claim 4, characterized in that: The image processing module includes an unqualified eye position determiner for determining whether an eye position photo is qualified, a horizontal adjuster, a locator for locating the eye position, a cropper and a nine-direction eye movement image generator, one end of the unqualified eye position determiner is electrically connected to one end of the horizontal adjuster, the other end of the horizontal adjuster and the other end of the feature extractor are both connected to one end of the locator, the other end of the locator is connected to one end of the cropper, and the other end of the cropper is connected to one end of the nine-direction eye movement image generator.

6. The ADHD assessment system based on eye movement according to claim 5, characterized in that: The unqualified eye position determiner determines whether the eye position photo is qualified according to a specific rule or algorithm, and deletes the photo if the eye position photo is unqualified.

7. The ADHD assessment system based on eye movement according to claim 6, characterized in that: The horizontal adjuster performs horizontal adjustment on the eye position photo with asymmetric sagittal plane of the image, so that the inner and outer canthus angles are adjusted to a horizontal position.

8. The ADHD assessment system based on eye movement according to claim 7, characterized in that: The cropper cuts the qualified eye position photo into a single photo at a ratio of 5:2 according to the set standard ratio, first positions it horizontally, and then positions it vertically in proportion to the eye position so that it is vertically centered.

9. The ADHD assessment system based on eye movement according to claim 8, characterized in that: The result output module uses computer vision algorithms and machine learning techniques to analyze the processed eye position photos, and then evaluates the eye position photos based on the output of the analysis results through set rules, thresholds or models, and then outputs the results to a suitable interface, and then displays the attention evaluation results in a graphical manner on a visualization interface.

10. The ADHD assessment system based on eye movement according to claim 9, characterized in that: The printing module includes an inkjet head for spraying pigment on a printing medium to form an image, an ink cartridge for providing ink to the inkjet head, a printing medium feeding device for guiding the printing medium for printing, a control circuit responsible for controlling the printing process, and a transmission system responsible for controlling and managing the movement between the inkjet head and the printing medium feeding device.

Images