Facial image acquisition system and method for adenoidal hypertrophy children

Abstract

The invention relates to the technical field of medical image acquisition, in particular to a facial image acquisition system and method for an adenoid hypertrophy child, and the method comprises the steps: S1, obtaining facial images of a subject at multiple angles through a camera; s2, forming a to-be-evaluated image set by using the acquired face images at the multiple angles; s3, performing qualification evaluation on images in the to-be-evaluated image data, namely judging whether the images in the to-be-evaluated image set are qualified or not, including evaluation of facial angles and evaluation of facial expression matching degrees; if yes, the step S6 is executed, and otherwise, the step S4 is executed; s4, outputting voice guidance information according to the judgment result of the previous step, and guiding the subject to adjust the rotation angle of the head; s5, obtaining the corresponding face image again, replacing the corresponding unqualified image with the newly obtained face image, storing the face image in the to-be-evaluated image set, and returning to the step S3; and S6, preprocessing the images in the to-be-evaluated image set, and sending the preprocessed images to the cloud.

Description

Technical Field

[0001] The present invention relates to the technical field of medical image acquisition, and in particular to a facial image acquisition system and method for children with adenoid hypertrophy. Background Art

[0002] Adenoids are lymphatic tissue located at the top of the nasopharynx and the posterior pharyngeal wall, and are part of the pharyngeal lymphatic ring. As children age, the adenoids also gradually increase in size. However, about 20% to 40% of children will experience excessive adenoid hyperplasia, which is called adenoid hypertrophy. This hypertrophy may lead to nasal obstruction and mouth breathing, which in turn leads to a variety of complications. Adenoid hypertrophy is one of the main causes of airway obstruction and can also cause specific maxillofacial deformities, forming the so-called "adenoid facies". The characteristics of this face include elongated mandible, high arched palate, narrow maxilla, protruding upper incisors, open lips and missing teeth, and lack of expression, which may make children look dull. Adenoid facies not only affects children's appearance, but may also have a negative impact on their mental health and social activities. In addition, long-term mouth breathing may also lead to decreased respiratory function in children, sleep apnea, inattention and poor academic performance.

[0003] For children with adenoids, doctors will routinely collect facial photos, including frontal face photos, frontal face smiling photos, left face 45° photos, right face 45° photos, left face 90° photos, and right face 90° photos. These photos have the following functions: Observe adenoid facies: Long-term mouth breathing may cause changes in facial morphology, and facial photos can help doctors observe and record these features; Record symptom changes: Facial photos can record children's facial changes before and after treatment to help doctors evaluate the treatment effect; Auxiliary diagnosis: Facial photos can be used as an auxiliary means of diagnosing adenoids, especially when children have typical adenoids facies; Parent communication: Showing parents photos of their children's faces can help explain the impact of adenoids and the need for treatment; Research and education: With the informed consent of the patient, facial photos can be used for medical research and education to help medical students and professionals better understand the clinical manifestations of adenoids.

[0004] Currently, the main way for clinicians to take photos of children's faces from different angles is to use handheld cameras or mobile phones. The shooting angle and quality of the photos are very dependent on the doctor's subjective judgment. Therefore, the quality of the pictures taken by doctors varies greatly and is difficult to be widely used for the above medical purposes. Therefore, there is an urgent need for a system that allows doctors to quickly and standardizedly collect children's facial images. Summary of the invention

[0005] The present invention can collect images from 6 different angles, evaluate whether the angles and facial expressions of the collected photos meet the requirements during the shooting process, and notify the person being collected to adjust the angle through the intelligent voice system to achieve the collection of standard pictures.

[0006] The technical solution provided by the present invention is: a method for collecting facial images of children with adenoid hypertrophy, the method comprising the following steps: S1. Obtain facial images of the subject at multiple angles through a camera, including a frontal image, a frontal smiling image, a left 45-degree image, a right 45-degree image, a left 90-degree image, and a right 90-degree image; S2, constructing an image set to be evaluated by using the facial images acquired at multiple angles; S3, performing qualification evaluation on the images in the image data to be evaluated, i.e., determining whether the images in the image set to be evaluated are qualified, including evaluation of facial angles and facial expression matching; if yes, proceeding to step S6, otherwise, proceeding to step S4; S4, according to the judgment result of the previous step, outputting voice guidance information to guide the subject to adjust the rotation angle of the head; S5, after the subject has completed the adjustment, the corresponding facial image is acquired again, and the corresponding unqualified image is replaced with the newly acquired facial image, stored in the image set to be evaluated, and the process returns to step S3; S6. Preprocess the images in the image set to be evaluated and send them to the cloud.

[0007] Preferably, the acquiring facial images of the subject at multiple angles through a camera includes: Turn on the camera and start capturing video stream data; Use the pre-trained face detection model Haar Cascade to detect faces in each frame; Import guidance voice data to guide the subject to turn his head; After detecting that the subject's head stops turning, the corresponding facial image is captured and the expected angle label is added.

[0008] Preferably, the evaluation of facial angles includes: Use the 68-point feature extractor of the pose estimation model Dlib to estimate the key points of the face in the facial image, thereby calculating the rotation angle of the head; According to the calculated angle, a calculated angle label is added to the corresponding facial image; Determine whether it is the required angle. If so, save the facial image of the frame and add an angle label. The required angles include front, left 45 degrees, left 90 degrees, right 45 degrees and right 90 degrees. The expected angle label and calculated angle label of the facial image are extracted, and the angle difference between the expected angle label and the calculated angle label is compared to see whether it meets the preset angle threshold, so as to determine whether the facial angle is qualified.

[0009] Preferably, the facial expression matching evaluation includes: Acquire a frontal facial image and recognize facial expressions in the frontal facial image; Determine whether the facial expression in the frontal facial image is a smile; If yes, the facial expression matching is judged to be qualified and the judgment result is output; otherwise, go to the next step; Generate voice call instruction three, call the voice guidance data, play the voice guidance data through the speaker, and remind the subject to adjust the facial expression and maintain a natural expression.

[0010] Preferably, the determining whether the facial expression of the person in the frontal facial image is a smile comprises: Use a pre-trained face detection model to detect faces and locate key facial features, including eyes, nose, and mouth. Use the pre-trained expression recognition model LBPH to determine whether the expression is a smile; specifically: Whether a smile is present is determined by calculating the degree of eye openness EAR. If EAR is lower than the threshold T and the condition is met for multiple consecutive frames, it is considered a smile.

[0011] Preferably, the facial expression matching evaluation further includes: Obtain a left 45 degree image and a right 45 degree image, and recognize facial expressions in the left 45 degree image and the right 45 degree image; Determine whether the facial expression in the left 45-degree image and the right 45-degree image is smiling; If not, the facial expression matching is judged to be qualified and the judgment result is output; otherwise, proceed to the next step; Generate voice call instruction three, call the voice guidance data, play the voice guidance data through the speaker, and remind the subject to adjust the facial expression and maintain a natural expression.

[0012] Preferably, outputting voice guidance information according to the judgment result of the previous step to guide the subject to adjust the rotation angle of the head includes: Compare the angle difference between the expected angle label and the calculated angle label to see if it meets a preset angle threshold; If the angle difference is less than the preset angle threshold , it is judged that the head rotation angle meets the acquisition requirements and the image is qualified; If the expected angle is less than the calculated angle, and the angle difference is greater than the preset angle threshold , it is judged that the head rotation angle is insufficient and does not meet the image acquisition requirements, a voice call instruction 1 is generated, voice guidance data is imported, and a voice reminder message that the head rotation angle is too small is output through the speaker to remind the subject to adjust the head rotation angle; If the expected angle is greater than the calculated angle, and the angle difference is greater than the preset angle threshold , it is judged that the head rotation angle is excessive and does not meet the image acquisition requirements, and a voice call instruction 2 is generated to import voice guidance data and output a voice reminder message that the head rotation angle is too large through the speaker to remind the subject to adjust the head rotation angle.

[0013] Preferably, the step of reminding the subject to adjust the head rotation angle comprises the following steps: generating a guidance voice list, wherein each line of the guidance voice list includes a calling instruction type and a voice text corresponding to the instruction type; Calling a corresponding voice text according to the received calling instruction type, wherein the calling instruction type includes voice calling instruction one and voice calling instruction two; Use a text-to-speech algorithm to convert the voice guidance data in text format into audio data that can be played using a speaker; The subject adjusts the head position according to the guidance voice heard, specifically including: continuing to turn the head in the original direction or turning the head in the opposite direction.

[0014] The present invention also provides a technical solution: a facial image acquisition system for children with adenoids hypertrophy, comprising a processor and a communication module connected to the processor, a memory, an image acquisition device, a speaker and a display, and the system is used to execute the facial image acquisition method for children with adenoids hypertrophy.

[0015] The present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement the method for acquiring facial images of children with adenoid hypertrophy.

[0016] Beneficial effects of the present invention: 1. The present invention can collect facial images of different angles and facial expressions, and evaluate whether the collected photos meet the requirements during the shooting process, including angle detection, angle and facial expression matching evaluation, etc., so as to judge whether the book is qualified. When the image angle is unqualified, different voice guidance information is called through voice call instruction 1 and voice call instruction 2 to guide the examinee to adjust the rotation angle of the head; when the angle and facial expression do not match, voice call instruction 3 is used to call voice guidance information to guide the examinee to adjust the facial expression.

[0017] 2. In the present invention, by constructing the feature vectors of the left and right eyes, the two feature vectors can not only determine the head rotation angle, but also be used to determine the facial expression of the subject, which can improve the speed of determining the rotation angle and facial expression. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 The present invention is a flow chart of a facial image acquisition method for children with adenoid hypertrophy. DETAILED DESCRIPTION

[0019] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art can think of other obvious variations. The basic principles of the present invention defined in the following description can be applied to other embodiments, variations, improvements, equivalents, and other technical solutions that do not deviate from the spirit and scope of the present invention.

[0020] It is to be understood that the term "one" should be understood as "at least one" or "one or more", that is, in one embodiment, the number of an element may be one, while in another embodiment, the number of the element may be multiple, and the term "one" should not be understood as a limitation on the quantity.

[0021] Please combine Figure 1 The present invention provides a method for collecting facial images of children with adenoid hypertrophy, and the specific steps are as follows: S1. Obtain facial images of the subject at multiple angles through a camera, including a frontal image, a frontal smiling image, a left 45-degree image, a right 45-degree image, a left 90-degree image, and a right 90-degree image; In this embodiment, this step can be implemented through the following process: Turn on the camera and start capturing video stream data; use the pre-trained face detection model Haar Cascade to detect faces in each frame; Import guidance voice data to guide the subject to turn his head; after detecting that the subject's head stops turning, take the corresponding facial image and add the expected angle label.

[0022] In some other embodiments, image data at different angles may also be acquired by acquiring static images.

[0023] S2, constructing an image set to be evaluated by using the facial images acquired at multiple angles; S3, performing qualification evaluation on the images in the image data to be evaluated, i.e., determining whether the images in the image set to be evaluated are qualified, including evaluation of facial angles and facial expression matching; if yes, proceeding to step S6, otherwise, proceeding to step S4; In this embodiment, the evaluation of facial angles can be achieved through the following process: The 68-point feature extractor of the pose estimation model Dlib is used to estimate the key points of the face in the facial image, so as to calculate the rotation angle of the head. Specifically, multiple feature points are selected from the left and right eyes to form the feature vectors of the left and right eyes. The rotation angle of the head is obtained by calculating the change of the feature vectors of the left and right eyes before and after the rotation. Specifically, it includes: Assume that the eigenvector before the head turns is: V = [x 1 ,y 1 , x 2 ,y 2 , ..., x n ,y n ], where (x i ,y i ) represents the coordinates of the i-th feature point; Suppose the eigenvector after the head is rotated is: V 1 =[x 11 ,y 11 , x 22 ,y 22 , ..., x nn ,y nn ]; Calculate V and V 1 Cosine similarity and convert to angle.

[0024] According to the calculated head rotation angle, a calculated angle label is added to the corresponding facial image; Determine whether it is the required angle. If so, save the facial image of the frame and add an angle label. The required angles include front, left 45 degrees, left 90 degrees, right 45 degrees and right 90 degrees. The expected angle label and calculated angle label of the facial image are extracted, and the angle difference between the expected angle label and the calculated angle label is compared to see whether it meets the preset angle threshold, so as to determine whether the facial angle is qualified.

[0025] In this embodiment, the facial expression matching evaluation can be achieved through the following process: Acquire a frontal facial image and recognize facial expressions in the frontal facial image;

[0026] Determine whether the facial expression in the frontal facial image is a smile; specifically, include: using a pre-trained facial detection model to detect the face and locate the key feature points of the face, including the eyes, nose, and mouth; using a pre-trained expression recognition model LBPH to determine whether the expression is a smile; the degree of eye openness EAR can be calculated to determine whether it is a smile, if the EAR is lower than the threshold T and multiple consecutive frames meet the conditions, it is considered a smile.

[0027] Or judging whether a smile is present is based on the change of the feature vector of the left eye or the feature vector of the right eye, specifically: In the left and right eyes, we select multiple feature points to form the feature vectors of the left and right eyes. These feature points usually include key positions such as the corners of the eyes, the corners of the mouth, and the eyebrows. By detecting the position and shape of these feature points, we can capture the changes in facial expressions.

[0028] For each frame of the image, we extract the coordinates of the feature points of the left and right eyes and combine them into a feature vector. This feature vector can be expressed as: V=[x 1 ,y 1 , x 2 ,y 2 , ..., x n ,y n ]where (x i ,y i ) represents the coordinates of the i-th feature point.

[0029] In order to determine whether a person is smiling, we need a baseline feature vector (i.e., the feature vector when there is no smile). Then, we compare the feature vector of the current frame with the baseline feature vector. If the difference between the two is within a certain threshold, we think the person is smiling; otherwise, we think the person is not smiling. The specific steps are as follows: In the absence of a smile, the feature vectors of the left and right eyes are recorded as the reference feature vectors. In the real-time video stream, the feature vectors of the left and right eyes of the current frame are continuously extracted. The Euclidean distance between the feature vector of the current frame and the reference feature vector is calculated. If the Euclidean distance is less than a preset threshold, it is judged as a smile; otherwise, it is not judged as a smile.

[0030] After the above judgment process, if the facial expression in the frontal image is judged to be a smile, the facial expression match is judged to be qualified and the judgment result is output; otherwise, a voice call instruction three is generated to call the voice guidance data, and the voice guidance data is played through the speaker to remind the subject to adjust the facial expression and maintain a natural expression.

[0031] S4, according to the judgment result of the previous step, outputting voice guidance information to guide the subject to adjust the rotation angle of the head; In this embodiment, this step can be implemented through the following process: Compare the angle difference between the expected angle label and the calculated angle label to see if it meets a preset angle threshold; If the angle difference is less than the preset angle threshold , it is judged that the head rotation angle meets the acquisition requirements and the image is qualified; If the expected angle is less than the calculated angle, and the angle difference is greater than the preset angle threshold , it is judged that the head rotation angle is insufficient and does not meet the image acquisition requirements, a voice call instruction 1 is generated, voice guidance data is imported, and a voice reminder message that the head rotation angle is too small is output through the speaker to remind the subject to adjust the head rotation angle; If the expected angle is greater than the calculated angle, and the angle difference is greater than the preset angle threshold , it is judged that the head rotation angle is excessive and does not meet the image acquisition requirements, and a voice call instruction 2 is generated to import voice guidance data and output a voice reminder message that the head rotation angle is too large through the speaker to remind the subject to adjust the head rotation angle.

[0032] S5, after the subject has completed the adjustment, the corresponding facial image is acquired again, and the corresponding unqualified image is replaced with the newly acquired facial image, stored in the image set to be evaluated, and the process returns to step S3; Among them, reminding the examinee to adjust the head rotation angle includes the following steps: generating a guidance voice list, wherein each line of the guidance voice list includes a calling instruction type and a voice text corresponding to the instruction type; Calling a corresponding voice text according to the received calling instruction type, wherein the calling instruction type includes voice calling instruction one and voice calling instruction two; Use a text-to-speech algorithm to convert the voice guidance data in text format into audio data that can be played using a speaker; The subject adjusts the head position according to the guidance voice heard, specifically including: continuing to turn the head in the original direction or turning the head in the opposite direction.

[0033] S6. Preprocess the images in the image set to be evaluated and send them to the cloud, including image denoising, contrast adjustment, format and size adjustment, etc.

[0034] The present invention also provides: a facial image acquisition system for children with adenoids hypertrophy, comprising a processor and a communication module connected to the processor, a memory, an image acquisition device and a display, wherein the system is used to execute the facial image acquisition method for children with adenoids hypertrophy.

[0035] The present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement the method for acquiring facial images of children with adenoid hypertrophy.

[0036] In the embodiments disclosed in the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. The embodiments disclosed in the present invention include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part, and / or installed from a removable medium. When the computer program is executed by the central processing unit (CPU), the above functions defined in the method of the present application are executed. It should be noted that the computer-readable medium mentioned above in the present application can be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium can be, for example, but not limited to, a system, device or device of an electrical, magnetic, optical, electromagnetic, infrared segment or semiconductor, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection with one or more wire segments, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In the present application, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries a computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, electrical wire, optical cable, RF, etc., or any suitable combination of the foregoing.

[0037] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present invention. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the module, a program segment or a part of a code contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the boxes can also occur in a different order than the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0038] Those skilled in the art should understand that the embodiments of the present invention described above and shown in the accompanying drawings are only examples and do not limit the present invention. The objectives of the present invention have been fully and effectively achieved. The functional and structural principles of the present invention have been demonstrated and explained in the embodiments. Without departing from the principles, the implementation methods of the present invention may be deformed or modified in any way.

Claims

1. A facial image acquisition method for children with adenoid hypertrophy, characterized in that: The method comprises the following steps: S1. Obtain facial images of the subject at multiple angles through a camera, including a frontal image, a frontal smiling image, a left 45-degree image, a right 45-degree image, a left 90-degree image, and a right 90-degree image; S2, constructing an image set to be evaluated by using the facial images acquired at multiple angles; S3, performing qualification evaluation on the images in the image data to be evaluated, i.e., determining whether the images in the image set to be evaluated are qualified, including evaluation of facial angles and facial expression matching; if yes, proceeding to step S6, otherwise, proceeding to step S4; S4, according to the judgment result of the previous step, outputting voice guidance information to guide the subject to adjust the rotation angle of the head; S5, after the subject has completed the adjustment, the corresponding facial image is acquired again, and the corresponding unqualified image is replaced with the newly acquired facial image, stored in the image set to be evaluated, and the process returns to step S3; S6. Preprocess the images in the image set to be evaluated and send them to the cloud.

2. The method for collecting facial images of children with adenoid hypertrophy according to claim 1, characterized in that: The method of obtaining facial images of the subject at multiple angles through a camera includes: Turn on the camera and start capturing video stream data; Use the pre-trained face detection model Haar Cascade to detect faces in each frame; Import guidance voice data to guide the subject to turn his head; After detecting that the subject's head stops turning, the corresponding facial image is captured and the expected angle label is added.

3. The facial image acquisition method for children with adenoid hypertrophy according to claim 2, characterized in that: The assessment of facial angles includes: Use the 68-point feature extractor of the pose estimation model Dlib to estimate the key points of the face in the facial image, thereby calculating the rotation angle of the head; According to the calculated angle, a calculated angle label is added to the corresponding facial image; Determine whether it is the required angle. If so, save the facial image of the frame and add an angle label. The required angles include front, left 45 degrees, left 90 degrees, right 45 degrees and right 90 degrees. The expected angle label and calculated angle label of the facial image are extracted, and the angle difference between the expected angle label and the calculated angle label is compared to see whether it meets the preset angle threshold, so as to determine whether the facial angle is qualified.

4. The facial image acquisition method for children with adenoid hypertrophy according to claim 3, characterized in that: The facial expression matching evaluation includes: Acquire a frontal facial image and recognize facial expressions in the frontal facial image; Determine whether the facial expression in the frontal facial image is a smile; If yes, the facial expression matching is judged to be qualified and the judgment result is output; otherwise, go to the next step; Generate voice call instruction three, call the voice guidance data, play the voice guidance data through the speaker, and remind the subject to adjust the facial expression and maintain a natural expression.

5. The method for collecting facial images of children with adenoid hypertrophy according to claim 4, characterized in that: The step of determining whether the facial expression of a person in the frontal facial image is a smile comprises: Use a pre-trained face detection model to detect faces and locate key facial features, including eyes, nose, and mouth. Use the pre-trained expression recognition model LBPH to determine whether the expression is a smile; specifically: Whether a smile is present is determined by calculating the degree of eye openness EAR. If EAR is lower than the threshold T and the condition is met for multiple consecutive frames, it is considered a smile.

6. The method for collecting facial images of children with adenoid hypertrophy according to claim 5, characterized in that: The facial expression matching evaluation also includes: Obtain a left 45 degree image and a right 45 degree image, and recognize facial expressions in the left 45 degree image and the right 45 degree image; Determine whether the facial expression in the left 45-degree image and the right 45-degree image is smiling; If not, the facial expression matching degree is judged to be qualified and the judgment result is output; otherwise, go to the next step; Generate voice call instruction three, call the voice guidance data, play the voice guidance data through the speaker, and remind the subject to adjust the facial expression and maintain a natural expression.

7. The method for collecting facial images of children with adenoid hypertrophy according to claim 6, characterized in that: The step of outputting voice guidance information according to the judgment result of the previous step to guide the subject to adjust the rotation angle of the head includes: Compare the angle difference between the expected angle label and the calculated angle label to see if it meets a preset angle threshold; If the angle difference is less than the preset angle threshold , it is judged that the head rotation angle meets the acquisition requirements and the image is qualified; If the expected angle is less than the calculated angle, and the angle difference is greater than the preset angle threshold , it is judged that the head rotation angle is insufficient and does not meet the image acquisition requirements, a voice call instruction 1 is generated, voice guidance data is imported, and a voice reminder message that the head rotation angle is too small is output through the speaker to remind the subject to adjust the head rotation angle; If the expected angle is greater than the calculated angle, and the angle difference is greater than the preset angle threshold , it is judged that the head rotation angle is excessive and does not meet the image acquisition requirements, and a voice call instruction 2 is generated to import voice guidance data and output a voice reminder message that the head rotation angle is too large through the speaker to remind the subject to adjust the head rotation angle.

8. The method for collecting facial images of children with adenoid hypertrophy according to claim 7, characterized in that: The method of reminding the examinee to adjust the head rotation angle comprises the following steps: generating a guidance voice list, wherein each line of the guidance voice list includes a calling instruction type and a voice text corresponding to the instruction type; Calling a corresponding voice text according to the received calling instruction type, wherein the calling instruction type includes voice calling instruction one and voice calling instruction two; Use a text-to-speech algorithm to convert the voice guidance data in text format into audio data that can be played using a speaker; The subject adjusts the head position according to the guidance voice heard, specifically including: continuing to turn the head in the original direction or turning the head in the opposite direction.

9. A facial image acquisition system for children with adenoid hypertrophy, comprising a processor and a communication module connected to the processor, a memory, an image acquisition device, a speaker and a display, characterized in that: The system is used to execute the facial image acquisition method of children with adenoid hypertrophy as described in any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement the facial image acquisition method for children with adenoid hypertrophy as described in any one of claims 1 to 8.

Images