Inner auditory canal intelligent self-detection method, system and storage medium

Abstract

The present application relates to an inner ear canal intelligent self-examination method, system and storage medium, and relates to the field of personal care medical examination technology, which includes: obtaining inner ear canal detection image information of the inspected person; identifying the inner ear canal identification position point from the inner ear canal detection image information according to the preset inner ear canal identification point feature; analyzing and obtaining standard identification image information from the inner ear canal detection image information according to the inner ear canal identification position point, the preset reference image information and the identification reference point; analyzing and outputting the normal image similarity rate and specific difference point annotation information between the standard identification image information and the normal inner ear canal detection image information according to the comparison result between the standard identification image information and the preset normal inner ear canal detection image information; using the normal image similarity rate and the specific difference point annotation information as the final detection result, and outputting the final detection result to the terminal held by the inspected person. The present application has the effect of facilitating the inspected person to inspect his or her own middle ear and inner ear alone.

Description

Technical Field

[0001] The present application relates to the field of personal care medical examination technology, and in particular to an inner auditory canal intelligent self-examination method, system and storage medium. Background Art

[0002] At present, with the improvement of people's living standards, people are also paying more and more attention to their own physical health. In daily life, before carrying out personal care to oneself, all need to carry out medical examination to oneself body, thus carry out special care.

[0003] In the related art, the ear has the function of receiving mechanical waves, converting sound waves into nerve signals, and then transmitting them to the brain, so that we can hear various sounds. It is one of our important organs. The ear consists of three parts: the outer ear, the middle ear and the inner ear. The outer ear includes the auricle and the external auditory canal, the middle ear includes the tympanic membrane, the tympanic cavity and the ossicles, and the inner ear includes the vestibule, the semicircular canals and the cochlea. The middle ear and the inner ear are located inside the human body and are not easy to inspect. When inspecting the middle ear and the inner ear, a visual otoscope is generally used as a simple inner ear canal inspection tool. By inserting the visual otoscope deep into the inner ear canal, the image of the inner ear canal is transmitted to the display, which makes it convenient for medical staff or other personnel in the hospital to inspect the middle ear and inner ear of the person being inspected according to the image in the display and inform the person being inspected of the test results.

[0004] With respect to the above-mentioned related technologies, the inventors have found the following defects: when examining the middle ear and inner ear of a person being examined through a visual otoscope, medical staff and other professionals are required to inform the person being examined of the test results based on the image displayed on the monitor, which makes it difficult for the person being examined to examine his or her middle ear and inner ear alone, and there is still room for improvement. Summary of the invention

[0005] In order to facilitate the examinee to examine his or her own middle ear and inner ear alone, the present application provides an inner auditory canal intelligent self-examination method, system and storage medium.

[0006] In a first aspect, the present application provides an inner auditory canal intelligent self-examination method, which adopts the following technical solution:

[0007] An inner auditory canal intelligent self-examination method, comprising:

[0008] Acquire the inner ear canal detection image information of the inspected person;

[0009] Identifying an inner auditory canal identification position point from the inner auditory canal detection image information according to a preset inner auditory canal identification point feature;

[0010] Analyze and obtain standard recognition image information from the inner auditory canal detection image information according to the inner auditory canal recognition position point, the preset reference image information and the recognition reference point;

[0011] According to the comparison result between the standard recognition image information and the preset normal inner ear canal detection image information, the normal image similarity rate and specific difference point marking information of the standard recognition image information and the normal inner ear canal detection image information are analyzed and output;

[0012] The normal image similarity and specific difference point marking information are used as the final detection result, and the final detection result is output to the terminal held by the person being tested.

[0013] By adopting the above technical scheme, the inner auditory canal detection image information of the inspected person is obtained, and the standard recognition image information is analyzed from the inner auditory canal detection image information to obtain the standard recognition image information, and the normal image similarity and specific difference point marking information are output by comparing the standard recognition image information with the normal inner auditory canal detection image information, and the normal image similarity and specific difference point marking information are used as the final detection result, and the final detection result is output to the terminal held by the inspected person, so that the inspected person can understand the detection results of his or her middle ear and inner ear through the terminal held, thereby improving the inspection accuracy of the middle ear and inner ear of the inspected person, and facilitating the inspected person to inspect his or her middle ear and inner ear alone.

[0014] Optionally, according to the inner auditory canal recognition position point, the preset reference image information and the recognition reference point, analyzing and acquiring the standard recognition image information from the inner auditory canal detection image information includes:

[0015] Determine whether the number of inner auditory canal identification position points corresponding to the number of preset identification reference points is consistent;

[0016] If yes, then obtaining edge position points of the reference image information and edge position points of the inner auditory canal detection image information;

[0017] According to the edge position points of the reference image information and the edge position points of the inner auditory canal detection image information, the reference points and the inner auditory canal recognition position points are identified, and the recognition image adjustment information is obtained by analyzing the inner auditory canal detection image information, and the recognition image adjustment information is used as the standard recognition image information;

[0018] If not, then according to the comparison relationship between the inner ear canal recognition position point, the inner ear canal missing recognition position point and the recognition reference point, analyze and obtain the inner ear canal missing recognition position point corresponding to the inner ear canal recognition position point and the recognition reference point;

[0019] According to the correspondence between the number of inner auditory canal missing identification position points and the preset first adjustment scheme, analyzing and obtaining the first adjustment scheme corresponding to the number of inner auditory canal missing identification position points;

[0020] According to the correspondence between the first adjustment scheme, the inner auditory canal detection image information and the standard recognition image information, the standard recognition image information corresponding to the first adjustment scheme and the inner auditory canal detection image information is analyzed and acquired.

[0021] By adopting the above technical solution, it is judged whether the number corresponding to the inner ear canal identification position points is consistent with the number corresponding to the preset identification reference points. When they are consistent, the identification image adjustment information is obtained based on the edge position points of the obtained reference image information and the edge position points of the inner ear canal detection image information, and the identification image adjustment information is used as the standard identification image information. When they are inconsistent, the inner ear canal missing identification position points are obtained based on the analysis of the inner ear canal identification position points and the identification reference points, and the first adjustment scheme is obtained based on the analysis of the number corresponding to the inner ear canal missing identification position points, so as to obtain the standard identification image information based on the first adjustment scheme analysis. By obtaining the standard identification image information, it is convenient to compare the standard identification image information with the normal inner ear canal detection image information in the future, thereby improving the accuracy of the detection.

[0022] Optionally, according to the edge position points of the reference image information and the edge position points of the inner auditory canal detection image information, the reference points and the inner auditory canal recognition position points are identified, and the identification image adjustment information is obtained from the inner auditory canal detection image information analysis, and the identification image adjustment information is used as the standard identification image information, including:

[0023] Obtain identification reference points and inner auditory canal identification position points;

[0024] The identification reference points and the inner auditory canal identification position points are respectively sorted in a forward direction, and the forward sorting is defined as the identification reference points are sorted in a clockwise order from the center of the reference image information to the outer circle, or the inner auditory canal identification position points are sorted in a clockwise order from the center of the inner auditory canal detection image information to the outer circle;

[0025] According to the one-to-one correspondence between the positively sorted recognition reference points and the positively sorted inner auditory canal recognition position points, the inner auditory canal detection image information is analyzed and adjusted, and the recognition image adjustment information is output.

[0026] By adopting the above technical solution, the recognition reference points and the inner auditory canal recognition position points are respectively sorted in positive order, and the positively sorted recognition reference points are matched one by one with the positively sorted inner auditory canal recognition position points, so as to analyze and adjust the inner auditory canal detection image information and output the recognition image adjustment information, thereby facilitating the subsequent comparison between the standard recognition image information and the normal inner auditory canal detection image information, thereby improving the accuracy of the detection.

[0027] Optionally, the method further includes the following steps: corresponding the recognition reference points sorted in the positive direction to the inner auditory canal recognition position points sorted in the positive direction one by one, analyzing and adjusting the inner auditory canal detection image information, and outputting the recognition image adjustment information:

[0028] The distance between the first identification reference point and the edge position point of the reference image information is obtained as the reference distance value, and the distance between the first inner auditory canal identification position point and the edge position point of the inner auditory canal detection image information is obtained as the actual distance value;

[0029] Determine whether the reference distance value is greater than the actual distance value;

[0030] If not, an alarm message is output to the terminal held by the inspected person;

[0031] If yes, differential image adjustment information is obtained from the inner auditory canal detection image information analysis according to the difference between the reference distance value and the actual distance value, and the differential image adjustment information is used as the standard recognition image information.

[0032] By adopting the above technical solution, it is determined whether the reference distance value is greater than the actual distance value, thereby determining whether the standard recognition image information can be obtained. When the reference distance value is not greater than the actual distance value, an alarm message is output to the terminal held by the person being tested. When the reference distance value is greater than the actual distance value, the inner auditory canal detection image information is adjusted according to the difference between the reference distance value and the actual distance value, and the difference image adjustment information is analyzed and obtained, and the difference image adjustment information is used as the standard recognition image information, thereby facilitating the analysis and acquisition of the standard recognition image information.

[0033] Optionally, obtaining difference image adjustment information from inner auditory canal detection image information analysis according to the difference between the reference distance value and the actual distance value includes:

[0034] Obtain the difference between the reference distance value and the actual distance value and use it as the adjustment difference;

[0035] Determine whether the adjustment difference is equal to a preset adjustment reference value;

[0036] If yes, output the recognition image adjustment information, and use the recognition image adjustment information as the difference image adjustment information;

[0037] If not, then according to the correspondence between the adjustment difference and the preset second adjustment solution, analyze and obtain the second adjustment solution corresponding to the adjustment difference;

[0038] According to the correspondence between the second adjustment scheme, the inner auditory canal detection image information and the difference image adjustment information, the difference image adjustment information corresponding to the second adjustment scheme and the inner auditory canal detection image information is analyzed and acquired.

[0039] By adopting the above technical solution, by judging whether the adjustment difference is equal to the preset adjustment reference value, it is judged whether the recognition image adjustment information needs to be adjusted. When the adjustment difference is equal to the preset adjustment reference value, the recognition image adjustment information is directly output, and the recognition image adjustment information is used as the difference image adjustment information. When the adjustment difference is not equal to the preset adjustment reference value, the second adjustment scheme is obtained according to the adjustment difference analysis, and then the difference image adjustment information is obtained according to the second adjustment scheme and the inner auditory canal detection image information analysis, so as to facilitate the acquisition of the difference image adjustment information.

[0040] Optionally, according to the correspondence between the number of inner auditory canal missing identification position points and a preset first adjustment scheme, analyzing and obtaining a first adjustment scheme corresponding to the number of inner auditory canal missing identification position points includes:

[0041] Determine whether the number of inner auditory canal missing identification position points is less than a preset reference number;

[0042] If not, an alarm message is output to the terminal held by the inspected person;

[0043] If yes, determining whether the inner auditory canal missing identification position point is a preset adjustment angle position point;

[0044] If yes, then according to the correspondence between the inner auditory canal missing identification position point and the preset adjustment angle scheme, an adjustment angle scheme corresponding to the inner auditory canal missing identification position point is analyzed and obtained, and the adjustment angle scheme is used as the first adjustment scheme;

[0045] If not, an alarm message is output to the terminal held by the inspected person.

[0046] By adopting the above technical solution, by judging whether the number corresponding to the missing inner ear canal identification position point is less than the preset reference number, it is judged whether the first adjustment scheme can be obtained to facilitate subsequent analysis and acquisition of standard recognition image information. When the number corresponding to the missing inner ear canal identification position point is not less than the preset reference number, an alarm message is output to the terminal held by the person being tested. When the number corresponding to the missing inner ear canal identification position point is less than the preset reference number, it is judged whether the missing inner ear canal identification position point is a preset adjustment angle position point. When the missing inner ear canal identification position point is a preset adjustment angle position point, an adjustment angle scheme is obtained based on the analysis of the missing inner ear canal identification position point, and the adjustment angle scheme is used as the first adjustment scheme. When the missing inner ear canal identification position point is not a preset adjustment angle position point, an alarm message is output to the terminal held by the person being tested, thereby improving the accuracy of the first adjustment scheme obtained.

[0047] Optionally, the method further includes a step of analyzing and outputting the normal image similarity rate and specific difference point marking information between the standard recognition image information and the normal inner auditory canal detection image information according to the comparison result between the standard recognition image information and the preset normal inner auditory canal detection image information, and before taking the normal image similarity rate and the specific difference point marking information as the final detection result and outputting the final detection result to the terminal held by the person being tested, which is specifically as follows:

[0048] Determine whether the normal image similarity is greater than a preset normal similarity reference value;

[0049] If yes, the normal image similarity and specific difference point marking information are output to the terminal held by the inspected person;

[0050] If the answer is no, then obtaining the disease inner ear canal detection image information, the disease inner ear canal detection image information including the tympanic membrane retraction inner ear canal detection image information, the tympanic membrane effusion inner ear canal detection image information and the tympanic membrane perforation inner ear canal detection image information;

[0051] According to the comparison result between the standard recognition image information and the tympanic membrane effusion inner ear canal detection image information, the tympanic membrane effusion image similarity rate and specific difference point marking information between the standard recognition image information and the tympanic membrane effusion inner ear canal detection image information are output;

[0052] According to the comparison result between the standard recognition image information and the tympanic membrane retraction inner ear canal detection image information, the similarity rate of the tympanic membrane retraction image and the specific difference point marking information between the standard recognition image information and the tympanic membrane retraction inner ear canal detection image information are output;

[0053] According to the comparison result between the standard recognition image information and the tympanic membrane perforation inner ear canal detection image information, the similarity rate of the tympanic membrane perforation image and the specific difference point marking information between the standard recognition image information and the tympanic membrane perforation inner ear canal detection image information are output;

[0054] The similarity rates of tympanic membrane effusion images, tympanic membrane retraction images, and tympanic membrane perforation images are used as the disease image similarity rates, and the disease image similarity rates and specific difference points are annotated to the terminal held by the person being examined.

[0055] By adopting the above technical solution, by judging whether the normal image similarity is greater than the preset normal similarity reference value, different detection results are increased. When the normal image similarity is greater than the preset normal similarity reference value, the normal image similarity and specific difference point marking information are directly output to the terminal held by the inspected person. When the normal image similarity is not greater than the preset normal similarity reference value, the image information is compared with the tympanic membrane effusion inner auditory canal detection image information, the tympanic membrane retraction inner auditory canal detection image information and the tympanic membrane perforation inner auditory canal detection image information according to the standard recognition image information, and the tympanic membrane effusion image similarity, the tympanic membrane retraction image similarity, the tympanic membrane perforation image similarity and the specific difference point marking information are output, and the tympanic membrane effusion image similarity, the tympanic membrane retraction image similarity and the tympanic membrane perforation image similarity are used as the symptom image similarity, and the symptom image similarity and the specific difference point marking information are sent to the terminal held by the examinee, so as to improve the inspection accuracy of the middle ear and inner ear of the examinee, and make it convenient for the examinee to examine his or her middle ear and inner ear alone, so that the examinee can understand his or her middle ear and inner ear.

[0056] Optionally, the similarity of tympanic membrane effusion images, tympanic membrane retraction images, and tympanic membrane perforation images as the disease image similarity includes:

[0057] Determine whether the similarity of the tympanic membrane effusion image, the similarity of the tympanic membrane retraction image, and the similarity of the tympanic membrane perforation image are all less than a preset minimum benchmark similarity;

[0058] If yes, the normal image similarity and specific difference point marking information are output to the terminal held by the inspected person;

[0059] If not, then positive sorting is performed based on one or more of the similarity rates of tympanic membrane effusion images, tympanic membrane retraction images, and tympanic membrane perforation images that are greater than the minimum benchmark similarity rate, and positive sorting is defined as sorting from large to small values;

[0060] According to the forward sorting result, one or more of the similarity rates of tympanic membrane effusion images, tympanic membrane retraction images, and tympanic membrane perforation images that are greater than the lowest benchmark similarity rate are output in sequence and used as the disease image similarity rate.

[0061] By adopting the above technical scheme, it is judged whether the similarity of the image of tympanic membrane effusion, the similarity of the image of tympanic membrane retraction, and the similarity of the image of tympanic membrane perforation are all less than the preset minimum benchmark similarity, so as to judge whether there is the possibility of tympanic membrane effusion, tympanic membrane retraction, and tympanic membrane perforation. When the similarity of the image of tympanic membrane effusion, the similarity of the image of tympanic membrane retraction, and the similarity of the image of tympanic membrane perforation are all less than the preset minimum benchmark similarity, the normal image similarity and specific difference point marking information are output to the terminal held by the person being inspected. When one or more of the similarities of tympanic membrane effusion images, tympanic membrane retraction images, and tympanic membrane perforation images are greater than a preset minimum benchmark similarity, forward sorting is performed based on the one or more of the similarities of tympanic membrane effusion images, tympanic membrane retraction images, and tympanic membrane perforation images that are greater than the minimum benchmark similarity, and one or more of the similarities of tympanic membrane effusion images, tympanic membrane retraction images, and tympanic membrane perforation images that are greater than the minimum benchmark similarity are output in sequence based on the forward sorting result, thereby improving the accuracy of the output result, improving the accuracy of the inspection of the middle ear and inner ear of the examinee, and making it convenient for the examinee to inspect his or her middle ear and inner ear alone, so that the examinee can understand his or her middle ear and inner ear.

[0062] In a second aspect, the present application provides an inner auditory canal intelligent self-examination system, which adopts the following technical solution:

[0063] An inner auditory canal intelligent self-examination system, comprising:

[0064] An acquisition module is used to: acquire the inner auditory canal detection image information of the person being examined;

[0065] The recognition module is used to: recognize the inner auditory canal recognition position point from the inner auditory canal detection image information according to the preset inner auditory canal recognition point features;

[0066] The first analysis module is used to analyze and obtain standard recognition image information from the inner auditory canal detection image information according to the inner auditory canal recognition position point, the preset reference image information and the recognition reference point;

[0067] The second analysis module is used to: analyze and output the normal image similarity rate and specific difference point marking information of the standard recognition image information and the normal inner auditory canal detection image information according to the comparison result of the standard recognition image information and the preset normal inner auditory canal detection image information;

[0068] The output module is used to: take the normal image similarity and specific difference point marking information as the final detection result, and output the final detection result to the terminal held by the person being tested.

[0069] By adopting the above technical scheme, the inner auditory canal detection image information of the inspected person is acquired through the acquisition module, and the inner auditory canal identification position point is identified through the recognition module, and then the standard identification image information is analyzed and acquired from the inner auditory canal detection image information through the first analysis module, and the second analysis module analyzes and outputs the normal image similarity and specific difference point marking information, and finally the final detection result is output to the terminal held by the inspected person through the output module, thereby improving the inspection accuracy of the middle ear and inner ear of the inspected person and making it convenient for the inspected person to inspect his or her own middle ear and inner ear alone.

[0070] In a third aspect, the present application provides a computer storage medium capable of storing corresponding programs, which has the characteristics of facilitating the improvement of the inspection accuracy of the middle ear and inner ear of the inspected person, and adopts the following technical solutions:

[0071] A computer storage medium stores a computer program that can be loaded by a processor and execute any one of the inner auditory canal intelligent self-examination methods of the first aspect.

[0072] By adopting the above technical solution, a computer program that can be loaded by a processor and execute any one of the inner auditory canal intelligent self-examination methods of the first aspect is stored through a computer storage medium, so that it can be used when needed, thereby improving the inspection accuracy of the middle ear and inner ear of the person being inspected.

[0073] In summary, the present application includes at least one of the following beneficial technical effects:

[0074] 1. By acquiring the inner ear canal detection image information of the inspected person, and analyzing the inner ear canal detection image information to obtain the standard recognition image information, by comparing the standard recognition image information with the normal inner ear canal detection image information, the normal image similarity and specific difference point marking information are output, and the normal image similarity and specific difference point marking information are used as the final detection result, and the final detection result is output to the terminal held by the inspected person, so that the inspected person can understand the detection results of his or her middle ear and inner ear through the terminal held, thereby improving the inspection accuracy of the middle ear and inner ear of the inspected person, and facilitating the inspected person to inspect his or her middle ear and inner ear alone;

[0075] 2. Determine whether the number corresponding to the inner auditory canal identification position points is consistent with the number corresponding to the preset identification reference points. When they are consistent, obtain and analyze the identification image adjustment information based on the edge position points of the obtained reference image information and the edge position points of the inner auditory canal detection image information, and use the identification image adjustment information as the standard identification image information. When they are inconsistent, obtain the inner auditory canal missing identification position points based on the analysis of the inner auditory canal identification position points and the identification reference points, and obtain the first adjustment plan based on the number corresponding to the inner auditory canal missing identification position points, and then obtain the standard identification image information based on the analysis of the first adjustment plan. By obtaining the standard identification image information, it is convenient to compare the standard identification image information with the normal inner auditory canal detection image information, thereby improving the accuracy of the detection;

[0076] 3. By judging whether the normal image similarity is greater than the preset normal similarity reference value, different detection results are increased. When the normal image similarity is greater than the preset normal similarity reference value, the normal image similarity and specific difference point marking information are directly output to the terminal held by the inspected person. When the normal image similarity is not greater than the preset normal similarity reference value, the image information is compared with the tympanic membrane effusion inner auditory canal detection image information, the tympanic membrane retraction inner auditory canal detection image information and the tympanic membrane perforation inner auditory canal detection image information according to the standard recognition image information, and the tympanic membrane effusion image similarity, the tympanic membrane retraction image similarity, the tympanic membrane perforation image similarity and the specific difference point marking information are output, and the tympanic membrane effusion image similarity, the tympanic membrane retraction image similarity and the tympanic membrane perforation image similarity are used as the symptom image similarity, and the symptom image similarity and the specific difference point marking information are sent to the terminal held by the examinee, thereby improving the inspection accuracy of the examinee's middle ear and inner ear, and making it convenient for the examinee to examine his or her middle ear and inner ear alone, so that the examinee can understand his or her middle ear and inner ear. BRIEF DESCRIPTION OF THE DRAWINGS

[0077] Figure 1 It is a flow chart of the method for intelligent self-examination of the inner auditory canal according to an embodiment of the present application.

[0078] Figure 2 This is a flow chart of a method for analyzing and acquiring standard recognition image information from inner auditory canal detection image information based on inner auditory canal recognition position points, preset reference image information and recognition reference points in another embodiment of the present application.

[0079] Figure 3 This is a flowchart of a method for another embodiment of the present application, which identifies reference points and inner auditory canal identification position points based on edge position points of reference image information and edge position points of inner auditory canal detection image information, analyzes inner auditory canal detection image information to obtain identification image adjustment information, and uses the identification image adjustment information as standard identification image information.

[0080] Figure 4 It is a method flow chart of another embodiment of the present application, which is located in a one-to-one correspondence between the positively sorted recognition reference points and the positively sorted inner auditory canal recognition position points, analyzes and adjusts the inner auditory canal detection image information, and outputs the recognition image adjustment information.

[0081] Figure 5 It is a flow chart of a method for obtaining difference image adjustment information from inner auditory canal detection image information according to the difference between a reference distance value and an actual distance value according to another embodiment of the present application.

[0082] Figure 6 It is a flowchart of a method for analyzing and obtaining a first adjustment scheme corresponding to the number of inner auditory canal missing identification position points according to the correspondence between the number of inner auditory canal missing identification position points and a preset first adjustment scheme in another embodiment of the present application.

[0083] Figure 7 It is a method flow chart of another embodiment of the present application, which is located after analyzing and outputting the normal image similarity and specific difference point marking information between the standard recognition image information and the normal inner auditory canal detection image information based on the comparison result between the standard recognition image information and the preset normal inner auditory canal detection image information, and before taking the normal image similarity and specific difference point marking information as the final detection result and outputting the final detection result to the terminal held by the person being tested.

[0084] Figure 8 This is a flow chart of a method for using the similarity of tympanic membrane effusion images, the similarity of tympanic membrane retraction images, and the similarity of tympanic membrane perforation images as the similarity of disease images in another embodiment of the present application.

[0085] Fig. 9 It is a structural schematic diagram of the inner auditory canal intelligent self-inspection system of an embodiment of the present application.

[0086] Explanation of the accompanying drawings: 1. Acquisition module; 2. Identification module; 3. First analysis module; 4. Second analysis module; 5. Output module. DETAILED DESCRIPTION

[0087] In order to make the purpose, technical solutions and advantages of this application more clear, the following Figure 1-9 It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0088] The embodiment of the present application discloses an inner auditory canal intelligent self-examination method.

[0089] When inspecting the middle ear and inner ear of the inspected person, medical staff or other personnel need to use a visual otoscopic scope to inspect the middle ear and inner ear of the inspected person, and then the medical staff or other personnel notify the inspected person of the inspection situation, and it is not easy for the inspected person to inspect his or her own middle ear and inner ear alone. When the inspected person uses a visual otoscopic scope to inspect the middle ear and inner ear of the inspected person, the inspected person's inner ear canal detection image information is obtained, and the inner ear canal detection image information is processed and compared with the normal inner ear canal detection image information to output the normal image similarity and specific difference point marking information, and output it as the final detection result to the terminal held by the inspected person, so that the inspected person can understand the detection results of his or her middle ear and inner ear through the terminal held, improve the inspection accuracy of the middle ear and inner ear of the inspected person, and facilitate the inspected person to inspect his or her own middle ear and inner ear alone.

[0090] Reference Figure 1 , an inner auditory canal intelligent self-examination method comprises:

[0091] Step S100, obtaining inner auditory canal detection image information of the person being examined.

[0092] The inner auditory canal detection image information refers to the detection information after the image of the inner auditory canal of the person being examined is captured, and the inner auditory canal detection image information is acquired through a camera installed on the visual otoscope.

[0093] Step S200: identifying inner auditory canal identification point from inner auditory canal detection image information according to preset inner auditory canal identification point features.

[0094] The inner ear canal identification point features are obtained by querying from a database storing the inner ear canal identification point features, and the inner ear canal identification point features refer to features in the inner ear canal that are easily identifiable, including but not limited to the eardrum boundary position point, the eardrum middle position point, and the eardrum protrusion position point in the inner ear canal. The inner ear canal detection image information is identified based on the inner ear canal identification point features, and the position of the identified inner ear canal identification point features is used as the inner ear canal identification position point.

[0095] Step S300, analyzing and acquiring standard recognition image information from the inner auditory canal detection image information according to the inner auditory canal recognition position point, the preset reference image information and the recognition reference point.

[0096] The reference image information is obtained from a database storing reference image information. The reference image information refers to an image of reference size and size required for subsequent steps. The identification reference point is obtained from a database storing identification reference points. The identification reference point refers to a reference position point for identifying a feature position required for subsequent steps in an image of reference size and size. The standard identification image information refers to a standard identification image whose angle and size meet the requirements of subsequent steps.

[0097] The reference image information is used to obtain the image of the reference size and size required for the subsequent steps from the inner auditory canal detection image information, and then the standard recognition image information is analyzed and obtained based on the position of the recognition reference point in the reference image and the position of the inner auditory canal recognition position point in the inner auditory canal detection image of the person being tested.

[0098] Step S400: Analyze and output the normal image similarity and specific difference point marking information between the standard recognition image information and the normal inner auditory canal detection image information according to the comparison result between the standard recognition image information and the preset normal inner auditory canal detection image information.

[0099] Among them, the normal inner auditory canal detection image information is queried and obtained from a database storing the normal inner auditory canal detection image information, and the normal inner auditory canal detection image information refers to the image detected in the normal inner auditory canal. The normal image similarity rate refers to the similarity percentage between the inner auditory canal detection image of the inspected person after it is converted into a standard recognition image and the image detected in the normal inner auditory canal. The specific difference point marking information refers to the specific difference position points between the inner auditory canal detection image of the inspected person after it is converted into a standard recognition image and the image detected in the normal inner auditory canal.

[0100] By comparing the standard recognition image information with the normal inner auditory canal detection image information, the normal image similarity and specific difference point marking information are analyzed and output.

[0101] Step S500: taking the normal image similarity and specific difference point marking information as the final detection result, and outputting the final detection result to the terminal held by the person being detected.

[0102] Among them, the final test result refers to the final output test information. The terminal held by the person being tested refers to a terminal that can receive and send data, which can be a mobile phone, a notebook, or other terminals that can receive and send data. By taking the normal image similarity and specific difference point annotation information as the final test result, and outputting the final test result to the terminal held by the person being tested, it is convenient for the person being tested to understand after checking his or her own inner auditory canal, improve the inspection accuracy of the middle ear and inner ear of the person being tested, and facilitate the person being tested to check his or her own middle ear and inner ear alone.

[0103] The implementation principle of the above steps is as follows: by obtaining the inner auditory canal detection image information of the inspected person and converting it into standard recognition image information, the standard recognition image information is compared with the normal inner auditory canal detection image information, thereby analyzing and outputting the normal image similarity and specific difference point marking information, and then using the normal image similarity and specific difference point marking information as the final detection result, and outputting the final detection result to the terminal held by the inspected person, so as to facilitate the inspected person to understand his or her own inner auditory canal after examination, improve the inspection accuracy of the middle ear and inner ear of the inspected person, and facilitate the inspected person to examine his or her own middle ear and inner ear alone.

[0104] exist Figure 1 In step S300, in order to further ensure the rationality of the standard recognition image information, it is necessary to further analyze and calculate the standard recognition image information. Figure 2 The steps shown are explained in detail.

[0105] Reference Figure 2 , according to the inner auditory canal recognition position point, the preset reference image information and the recognition reference point, analyzing and obtaining the standard recognition image information from the inner auditory canal detection image information includes the following steps:

[0106] Step S310, determining whether the number of inner auditory canal identification position points corresponds to the number of preset identification reference points. If yes, executing step S320; if no, executing step S340.

[0107] Among them, by judging whether the number corresponding to the inner auditory canal identification position points is consistent with the number corresponding to the preset identification reference points, it is judged whether the obtained inner auditory canal detection image information meets subsequent needs.

[0108] Step S320, obtaining edge position points of the reference image information and edge position points of the inner auditory canal detection image information.

[0109] The edge position point of the reference image information refers to the position coordinates of the edge position in the reference image. The edge position point of the inner auditory canal detection image information refers to the position coordinates of the edge position in the inner auditory canal detection image of the subject.

[0110] When the number of inner auditory canal identification position points is consistent with the number of preset identification reference points, it means that the acquired inner auditory canal detection image information meets subsequent needs, so the edge position points of the reference image information and the edge position points of the inner auditory canal detection image information are directly acquired.

[0111] Step S330, identifying the reference point and the inner auditory canal identification position point according to the edge position points of the reference image information and the edge position points of the inner auditory canal detection image information, analyzing the inner auditory canal detection image information to obtain the identification image adjustment information, and using the identification image adjustment information as the standard identification image information.

[0112] The recognition image adjustment information refers to extracting an image that is convenient for subsequent steps to be operated from the inner auditory canal detection image information after recognition.

[0113] By comparing the edge position points of the reference image information with the edge position points of the inner auditory canal detection image information, identifying the reference points and the inner auditory canal identification position points, the identification image adjustment information is obtained from the inner auditory canal detection image information analysis, and the identification image adjustment information is used as the standard identification image information.

[0114] Step S340, based on the comparison relationship between the inner auditory canal identification position point, the inner auditory canal missing identification position point and the identification reference point, analyze and obtain the inner auditory canal missing identification position point corresponding to the inner auditory canal identification position point and the identification reference point.

[0115] The missing inner auditory canal identification position point refers to a position point where the inner auditory canal identification position point in the inner auditory canal detection image of the person being examined is missing.

[0116] When the number of inner auditory canal identification position points corresponding to the number of preset identification reference points is inconsistent, it means that the obtained inner auditory canal detection image information does not meet subsequent needs. By comparing the inner auditory canal identification position points and the identification reference points, the missing identification position points of the inner auditory canal are analyzed and obtained, thereby facilitating the use of subsequent operation steps.

[0117] Step S350, according to the correspondence between the number of inner auditory canal missing identification position points and the preset first adjustment scheme, analyze and obtain the first adjustment scheme corresponding to the number of inner auditory canal missing identification position points.

[0118] The first adjustment scheme is obtained by querying a database storing the first adjustment scheme, and the first adjustment scheme refers to a scheme for adjusting the inner auditory canal detection image information. The first adjustment scheme is obtained by analyzing the number of inner auditory canal missing identification position points, so as to facilitate the use of subsequent operation steps.

[0119] Step S360: Analyze and obtain standard recognition image information corresponding to the first adjustment scheme and the inner auditory canal detection image information according to the correspondence between the first adjustment scheme, the inner auditory canal detection image information and the standard recognition image information.

[0120] The standard recognition image information is obtained through the first adjustment scheme and the analysis of the inner auditory canal detection image information, thereby improving the accuracy of the obtained standard recognition image information.

[0121] The implementation principle of the above steps is as follows: by judging whether the number corresponding to the inner auditory canal identification position points is consistent with the number corresponding to the preset identification reference points, it is judged whether the obtained inner auditory canal detection image information meets the subsequent needs. When the number corresponding to the inner auditory canal identification position points is consistent with the number corresponding to the preset identification reference points, the identification image adjustment information is obtained by analyzing the edge position points of the obtained reference image information and the edge position points of the inner auditory canal detection image information, and the identification image adjustment information is used as the standard identification image information. When the number corresponding to the inner auditory canal identification position points is inconsistent with the number corresponding to the preset identification reference points, the inner auditory canal missing identification position points are obtained by analyzing the inner auditory canal identification position points and the identification reference points, and then the first adjustment scheme is obtained by analyzing the number corresponding to the inner auditory canal missing identification position points, and finally the standard identification image information is obtained by analyzing the first adjustment scheme and the inner auditory canal detection image information, thereby improving the accuracy of the obtained standard identification image information.

[0122] exist Figure 2 In step S330, in order to further ensure the rationality of the standard recognition image information, it is necessary to further analyze and calculate the standard recognition image information. Figure 3 The steps shown are explained in detail.

[0123] Reference Figure 3 , identifying the reference point and the inner auditory canal identification position point according to the edge position point of the reference image information and the edge position point of the inner auditory canal detection image information, analyzing the inner auditory canal detection image information to obtain the identification image adjustment information, and using the identification image adjustment information as the standard identification image information includes the following steps:

[0124] Step S331, obtaining the identification reference point and the inner auditory canal identification position point.

[0125] Step S332, sorting the identification reference points and the inner auditory canal identification position points in a forward direction respectively.

[0126] The forward sorting is defined as the identification reference points being sorted in a clockwise order from the reference image information center to the outer circle, and the inner auditory canal identification position points are also sorted in a clockwise order from the inner auditory canal detection image information center to the outer circle.

[0127] Step S333: Analyze and adjust the inner auditory canal detection image information according to the one-to-one correspondence between the positively sorted recognition reference points and the positively sorted inner auditory canal recognition position points, and output recognition image adjustment information.

[0128] Among them, the one-to-one correspondence between the positively sorted identification reference points and the positively sorted inner auditory canal identification position points means that after the identification reference points and the inner auditory canal identification position points are positively sorted, the identification reference points and the inner auditory canal identification position points at the same sorting position are one-to-one corresponded. By the one-to-one correspondence between the positively sorted identification reference points and the positively sorted inner auditory canal identification position points, the inner auditory canal detection image information is adjusted, and the identification image adjustment information is output, so as to improve the accuracy of the obtained identification image adjustment information, thereby facilitating the use of subsequent operation steps.

[0129] The implementation principle of the above steps is as follows: by positively sorting the recognition reference points and the inner auditory canal recognition position points respectively, and corresponding the positively sorted recognition reference points with the positively sorted inner auditory canal recognition position points one by one, the inner auditory canal detection image information is adjusted, and the recognition image adjustment information is output, thereby improving the accuracy of the obtained recognition image adjustment information, thereby facilitating the use of subsequent operation steps.

[0130] exist Figure 3 After step S333, in order to further ensure the rationality of the standard recognition image information, it is necessary to further analyze and calculate the standard recognition image information. Figure 4 The steps shown are explained in detail.

[0131] Reference Figure 4 , the steps after the recognition reference points arranged in the positive order correspond to the inner auditory canal recognition position points arranged in the positive order, analyzing and adjusting the inner auditory canal detection image information and outputting the recognition image adjustment information include the following steps:

[0132] Step S334, obtaining the distance between the first identification reference point and the edge position point of the reference image information as the reference distance value, and obtaining the distance between the first inner auditory canal identification position point and the edge position point of the inner auditory canal detection image information as the actual distance value.

[0133] Among them, the first identification reference point refers to the identification reference point that is in the first sorting position after the identification reference points are sorted in the forward direction, and the first inner auditory canal identification position point refers to the inner auditory canal identification position point that is in the first sorting position after the inner auditory canal identification position points are sorted in the forward direction. The distance between the first identification reference point and the edge position point of the reference image information is used as the reference distance value. The distance between the first inner auditory canal identification position point and the edge position point of the inner auditory canal detection image information is used as the actual distance value.

[0134] Step S335, determine whether the reference distance value is greater than the actual distance value. If not, execute step S336; if yes, execute step S337.

[0135] Here, by judging whether the reference distance value is greater than the actual distance value, it is judged whether the inner auditory canal detection image of the person under examination can be converted into a standard recognition image.

[0136] Step S336, outputting alarm information to the terminal held by the inspected person.

[0137] Among them, when the reference distance value is not greater than the actual distance value, it means that the size of the inner auditory canal detection image of the inspected person is smaller than the size of the standard recognition image, which means that the inner auditory canal detection image of the inspected person cannot be converted into the standard recognition image. Therefore, an alarm message is directly output to the terminal held by the inspected person, thereby prompting the inspected person to re-acquire the inner auditory canal detection image of the inspected person.

[0138] Step S337, obtaining difference image adjustment information from the inner auditory canal detection image information according to the difference between the reference distance value and the actual distance value, and using the difference image adjustment information as standard recognition image information.

[0139] Among them, when the reference distance value is greater than the actual distance value, it means that the size of the inner auditory canal detection image of the subject is greater than or equal to the size of the standard recognition image, which means that the inner auditory canal detection image of the subject can be converted into a standard recognition image. Therefore, the difference between the reference distance value and the actual distance value is used to analyze the inner auditory canal detection image information to obtain the difference image adjustment information, and the difference image adjustment information is used as the standard recognition image information, so as to facilitate the use in subsequent operation steps.

[0140] The implementation principle of the above steps is as follows: by judging whether the reference distance value is greater than the actual distance value, it is judged whether the inner ear canal detection image of the person under test can be converted into a standard recognition image. When the reference distance value is not greater than the actual distance value, an alarm message is output to the terminal held by the person under test, thereby prompting the person under test to re-acquire the inner ear canal detection image of the person under test. When the reference distance value is greater than the actual distance value, the difference image adjustment information is obtained from the inner ear canal detection image information analysis through the difference between the reference distance value and the actual distance value, and the difference image adjustment information is used as the standard recognition image information, so as to facilitate the use of subsequent operation steps.

[0141] exist Figure 4 In step S336, in order to further ensure the rationality of the standard recognition image information, it is necessary to further analyze and calculate the standard recognition image information. Figure 5 The steps shown are explained in detail.

[0142] Reference Figure 5 , obtaining difference image adjustment information from the inner auditory canal detection image information analysis according to the difference between the reference distance value and the actual distance value includes the following steps:

[0143] Step S3361, obtaining the difference between the reference distance value and the actual distance value, and using it as the adjustment difference.

[0144] The difference between the reference distance value and the actual distance value is obtained, and the difference between the reference distance value and the actual distance value is used as the adjustment difference.

[0145] Step S3362, determine whether the adjustment difference is equal to the preset adjustment reference value. If yes, execute step S3363; if no, execute step S3364.

[0146] The adjustment reference value is obtained by querying from a database storing the adjustment reference value, and the adjustment reference value refers to a reference difference between a reference distance value and an actual distance value.

[0147] By judging whether the adjustment difference is equal to the preset adjustment reference value, it is judged whether the difference between the reference distance value and the actual distance value is equal to the reference difference between the reference distance value and the actual distance value.

[0148] Step S3363: output the recognition image adjustment information, and use the recognition image adjustment information as the difference image adjustment information.

[0149] Among them, when the adjustment difference is equal to the preset adjustment reference value, it means that the difference between the reference distance value and the actual distance value is equal to the reference difference between the reference distance value and the actual distance value. At this time, there is no need to adjust the recognition image adjustment information, and the recognition image adjustment information is directly used as the difference image adjustment information.

[0150] Step S3364: Analyze and obtain the second adjustment scheme corresponding to the adjustment difference according to the corresponding relationship between the adjustment difference and the preset second adjustment scheme.

[0151] The second adjustment scheme refers to an adjustment scheme for adjusting the inner auditory canal detection image information, that is, scaling the size of the inner auditory canal detection image according to the numerical value of the adjustment difference.

[0152] When the adjustment difference is not equal to the preset adjustment reference value, it means that the difference between the reference distance value and the actual distance value is not equal to the reference difference between the reference distance value and the actual distance value, and the second adjustment scheme is obtained through adjustment difference analysis.

[0153] Step S3365: Analyze and obtain the difference image adjustment information corresponding to the second adjustment scheme and the inner auditory canal detection image information according to the correspondence between the second adjustment scheme, the inner auditory canal detection image information and the difference image adjustment information.

[0154] Among them, the second adjustment scheme and the inner auditory canal detection image information are used to scale the size of the inner auditory canal detection image, and the difference image adjustment information is analyzed and obtained, so as to facilitate the use of subsequent operation steps.

[0155] The implementation principle of the above steps is as follows: by judging whether the adjustment difference is equal to the preset adjustment reference value, it is judged whether the difference between the reference distance value and the actual distance value is equal to the reference difference between the reference distance value and the actual distance value. When the adjustment difference is equal to the preset adjustment reference value, the recognition image adjustment information is directly used as the difference image adjustment information. When the adjustment difference is not equal to the preset adjustment reference value, the second adjustment scheme is obtained by adjusting the difference analysis, and the size of the inner auditory canal detection image is scaled by the second adjustment scheme and the inner auditory canal detection image information, and the difference image adjustment information is analyzed and obtained, so as to facilitate the use of subsequent operation steps.

[0156] exist Figure 2 In step S350, in order to further ensure the rationality of the first adjustment scheme, it is necessary to further analyze and calculate the first adjustment scheme. Figure 6 The steps shown are explained in detail.

[0157] Reference Figure 6 According to the correspondence between the number of inner auditory canal missing identification position points and the preset first adjustment scheme, analyzing and obtaining the first adjustment scheme corresponding to the number of inner auditory canal missing identification position points includes the following steps:

[0158] Step S351, determining whether the number of inner auditory canal missing identification position points is less than a preset reference number. If not, executing step S352; if yes, executing step S353.

[0159] Wherein, by judging whether the number of the inner auditory canal missing identification position points is less than a preset reference number, it is judged whether the inner auditory canal detection image can be adjusted through the first adjustment scheme.

[0160] Step S352: output alarm information to the terminal held by the inspected person.

[0161] Among them, when the number corresponding to the missing identification position points of the inner auditory canal is not less than the preset benchmark number, it means that the inner auditory canal detection image cannot be adjusted through the first adjustment scheme at this time, so the alarm information is directly output to the terminal held by the inspected person, thereby prompting the inspected person to re-acquire the inner auditory canal detection image of the inspected person.

[0162] Step S353, determining whether the inner auditory canal missing identification position point is a preset adjustment angle position point. If yes, executing step S354; if no, executing step S355.

[0163] The adjusted angle position point is obtained by querying from a database storing the adjusted angle position point, and the adjusted angle position point refers to a position point that can be converted into a standard recognition image after adjusting the angle of the inner auditory canal detection image.

[0164] When the number of inner ear canal missing identification position points is less than the preset reference number, it means that the inner ear canal detection image can be adjusted by the first adjustment scheme. Then, it is judged whether the inner ear canal missing identification position point is a preset adjustment angle position point, thereby judging whether the inner ear canal detection image can be adjusted by the first adjustment scheme.

[0165] Step S354, according to the correspondence between the inner auditory canal missing identification position point and the preset adjustment angle scheme, analyze and obtain the adjustment angle scheme corresponding to the inner auditory canal missing identification position point, and use the adjustment angle scheme as the first adjustment scheme.

[0166] The angle adjustment scheme is obtained by querying from a database storing the angle adjustment schemes, and the angle adjustment scheme refers to a scheme that can convert the inner auditory canal detection image into a standard recognition image after adjusting the angle.

[0167] When the inner auditory canal missing identification position point is a preset adjustment angle position point, it means that the inner auditory canal detection image can be adjusted through the first adjustment scheme, the adjustment angle scheme is obtained through the analysis of the inner auditory canal missing identification position point, and the adjustment angle scheme is used as the first adjustment scheme.

[0168] Step S355, outputting alarm information to the terminal held by the inspected person.

[0169] Among them, when the inner auditory canal missing identification position point is not the preset adjustment angle position point, it means that the inner auditory canal detection image cannot be adjusted through the first adjustment scheme, so the alarm information is directly output to the terminal held by the inspected person, thereby prompting the inspected person to re-acquire the inner auditory canal detection image of the inspected person.

[0170] The implementation principle of the above steps is as follows: by judging whether the number corresponding to the missing inner ear canal identification position points is less than the preset reference number, it is judged whether the inner ear canal detection image can be adjusted through the first adjustment scheme. When the number corresponding to the missing inner ear canal identification position points is less than the preset reference number, and when the missing inner ear canal identification position points are preset adjustment angle position points, the adjustment angle scheme is obtained through the analysis of the missing inner ear canal identification position points, and the adjustment angle scheme is used as the first adjustment scheme. Otherwise, an alarm message is directly output to the terminal held by the person being tested, thereby prompting the person being tested to re-obtain the inner ear canal detection image of the person being tested, thereby improving the accuracy of the first adjustment scheme obtained.

[0171] exist Figure 1 After step S400 and before step S500, in order to further ensure the rationality of the standard recognition image information, it is necessary to further analyze and calculate the standard recognition image information. Figure 7 The steps shown are explained in detail.

[0172] Reference Figure 7 , after analyzing and outputting the normal image similarity rate and specific difference point marking information between the standard recognition image information and the normal inner auditory canal detection image information according to the comparison result between the standard recognition image information and the preset normal inner auditory canal detection image information, and before taking the normal image similarity rate and the specific difference point marking information as the final detection result and outputting the final detection result to the terminal held by the person being tested, the steps include the following steps:

[0173] Step S410, determining whether the normal image similarity is greater than a preset normal similarity reference value. If yes, executing step S420; if no, executing step S430.

[0174] Among them, the normal similarity rate benchmark value is obtained by querying from a database storing the normal similarity rate benchmark value. The normal similarity rate benchmark value refers to the minimum tolerable similarity percentage between the image detected in the normal inner auditory canal after the inner auditory canal detection image of the examined person is converted into a standard recognition image.

[0175] By judging whether the normal image similarity is greater than a preset normal similarity reference value, it is judged whether the inner auditory canal detection image of the examined person has a high degree of similarity with the image detected in the normal inner auditory canal after being converted into a standard recognition image.

[0176] Step S420: output the normal image similarity and specific difference point marking information to the terminal held by the person being inspected.

[0177] Among them, when the normal image similarity is greater than the preset normal similarity benchmark value, it means that the inner auditory canal detection image of the inspected person is converted into a standard recognition image and has a high degree of similarity with the image detected in the normal inner auditory canal. Therefore, the normal image similarity and specific difference point marking information are directly output to the terminal held by the inspected person.

[0178] Step S430, obtaining diseased inner auditory canal detection image information.

[0179] Among them, the disease inner auditory canal detection image information includes the inner auditory canal detection image information of tympanic membrane retraction, the inner auditory canal detection image information of tympanic membrane effusion and the inner auditory canal detection image information of tympanic membrane perforation.

[0180] The inner ear canal detection image information of the retracted tympanic membrane refers to the inner ear canal detection image with the retracted tympanic membrane. The inner ear canal detection image information of the tympanic membrane effusion refers to the inner ear canal detection image with the tympanic membrane effusion. The inner ear canal detection image information of the tympanic membrane perforation refers to the inner ear canal detection image with the tympanic membrane perforation.

[0181] When the normal image similarity is not greater than the preset normal similarity benchmark value, it means that there is a large difference between the inner auditory canal detection image of the subject after being converted into a standard recognition image and the image detected in the normal inner auditory canal, so the diseased inner auditory canal detection image information is obtained.

[0182] Step S440, based on the comparison result between the standard recognition image information and the tympanic membrane effusion inner auditory canal detection image information, output the tympanic membrane effusion image similarity rate and specific difference point marking information between the standard recognition image information and the tympanic membrane effusion inner auditory canal detection image information.

[0183] The similarity rate of the tympanic membrane effusion image refers to the similarity percentage between the inner auditory canal detection image of the subject after it is converted into a standard recognition image and the inner auditory canal detection image with tympanic membrane effusion.

[0184] By comparing the standard recognition image with the tympanic membrane effusion inner auditory canal detection image, the similarity rate of the tympanic membrane effusion image and the specific difference point annotation information are output.

[0185] Step S450, based on the comparison result between the standard recognition image information and the tympanic membrane retraction inner auditory canal detection image information, output the tympanic membrane retraction image similarity and specific difference point marking information between the standard recognition image information and the tympanic membrane retraction inner auditory canal detection image information.

[0186] The similarity rate of the tympanic membrane retraction image refers to the similarity percentage between the inner auditory canal detection image of the subject after it is converted into a standard recognition image and the inner auditory canal detection image with tympanic membrane retraction.

[0187] By comparing the standard recognition image with the inner auditory canal detection image of the retracted tympanic membrane, the similarity rate of the retracted tympanic membrane image and the specific difference point marking information are output.

[0188] Step S460, based on the comparison result between the standard recognition image information and the tympanic membrane perforation inner auditory canal detection image information, output the tympanic membrane perforation image similarity and specific difference point marking information between the standard recognition image information and the tympanic membrane perforation inner auditory canal detection image information.

[0189] The similarity rate of the tympanic membrane perforation image refers to the similarity percentage between the inner auditory canal detection image of the subject after it is converted into a standard recognition image and the inner auditory canal detection image with tympanic membrane perforation.

[0190] By comparing the standard recognition image with the inner ear canal detection image of the tympanic membrane perforation, the similarity rate of the tympanic membrane perforation image and the specific difference point annotation information are output.

[0191] Step S470, taking the similarity of tympanic membrane effusion image, tympanic membrane retraction image and tympanic membrane perforation image as the similarity of the disease image, and marking the similarity of the disease image and specific difference points to the terminal held by the person being examined.

[0192] Among them, the similarity rates of tympanic membrane effusion images, tympanic membrane retraction images, and tympanic membrane perforation images are used as the similarity rates of disease images, and the disease image similarity rates and specific difference point annotation information are sent to the terminal held by the examinee, thereby improving the accuracy of the examination of the examinee's middle ear and inner ear, and making it convenient for the examinee to examine his or her own middle ear and inner ear alone, so that the examinee can understand his or her own middle ear and inner ear.

[0193] The implementation principle of the above steps is as follows: by judging whether the normal image similarity is greater than the preset normal similarity reference value, it is judged whether the inner ear canal detection image of the inspected person is highly similar to the image detected in the normal inner ear canal after being converted into a standard recognition image. When the normal image similarity is greater than the preset normal similarity reference value, the normal image similarity and specific difference point marking information are directly output to the terminal held by the inspected person.

[0194] When the normal image similarity is not greater than the preset normal similarity reference value, the disease inner ear canal detection image information is obtained, and compared with the tympanic membrane effusion inner ear canal detection image, the tympanic membrane retraction inner ear canal detection image and the tympanic membrane perforation inner ear canal detection image respectively through the standard recognition image, so as to output the tympanic membrane effusion image similarity, the tympanic membrane retraction image similarity and the tympanic membrane perforation image similarity. The tympanic membrane effusion image similarity, the tympanic membrane retraction image similarity and the tympanic membrane perforation image similarity are used as the disease image similarity, and the disease image similarity and specific difference point annotation information are sent to the terminal held by the person being examined, thereby improving the inspection accuracy of the middle ear and inner ear of the person being examined, and facilitating the person being examined to examine his own middle ear and inner ear alone, so that the person being examined can understand his own middle ear and inner ear.

[0195] exist Figure 7 In step S470, in order to further ensure the rationality of the disease image similarity, it is necessary to further analyze and calculate the disease image similarity. Figure 8 The steps shown are explained in detail.

[0196] Reference Figure 8 , using the similarity of tympanic membrane effusion images, the similarity of tympanic membrane retraction images, and the similarity of tympanic membrane perforation images as the disease image similarity includes the following steps:

[0197] Step S471, determining whether the similarity of the tympanic membrane effusion image, the tympanic membrane retraction image, and the tympanic membrane perforation image are all less than a preset minimum reference similarity. If yes, executing step S472; if no, executing step S473.

[0198] Among them, the minimum benchmark similarity is obtained by querying from a database storing the minimum benchmark similarity. The minimum benchmark similarity refers to the minimum tolerable similarity percentage between the image of the inner auditory canal detection of the subject after it is converted into a standard recognition image and the image detected in the inner auditory canal with the disease.

[0199] By judging whether the similarity rates of tympanic membrane effusion images, tympanic membrane retraction images, and tympanic membrane perforation images are all less than the preset minimum benchmark similarity rates, it is judged whether the inner auditory canal detection image of the subject, after being converted into a standard recognition image, has a high degree of similarity with the image detected in the inner auditory canal of the diseased person.

[0200] Step S472, output the normal image similarity and specific difference point marking information to the terminal held by the person being inspected.

[0201] Among them, when the similarity rates of tympanic membrane effusion images, tympanic membrane retraction images, and tympanic membrane perforation images are all less than the preset minimum benchmark similarity rates, it means that there is a large difference between the image of the inner auditory canal detection of the person being examined after being converted into a standard recognition image and the image detected in the inner auditory canal with the disease, so the normal image similarity rate and specific difference point marking information are output to the terminal held by the person being examined.

[0202] Step S473, performing forward sorting according to one or more of the similarity rates of tympanic membrane effusion images, tympanic membrane retraction images, and tympanic membrane perforation images that are greater than the minimum reference similarity rate.

[0203] The forward sorting is defined as sorting the corresponding values ​​of the similarity of tympanic membrane effusion images, the similarity of tympanic membrane retraction images, and the similarity of tympanic membrane perforation images from large to small.

[0204] When one or more of the similarity rates of tympanic membrane effusion images, tympanic membrane retraction images, and tympanic membrane perforation images are greater than the preset minimum benchmark similarity rate, it indicates that the inner auditory canal detection image of the subject after being converted into a standard recognition image has a high similarity with the image detected in the inner auditory canal with the disease. Therefore, one or more of the similarity rates of tympanic membrane effusion images, tympanic membrane retraction images, and tympanic membrane perforation images that are greater than the minimum benchmark similarity rate are positively sorted.

[0205] Step S474, according to the forward sorting result, one or more of the similarity rates of tympanic membrane effusion images, tympanic membrane retraction images, and tympanic membrane perforation images that are greater than the minimum benchmark similarity rate are output in sequence and used as the disease image similarity rate.

[0206] Among them, one or more of the similarities of tympanic membrane effusion images, tympanic membrane retraction images, and tympanic membrane perforation images that are greater than the minimum benchmark similarity are output in sequence through the forward sorting results, and one or more of the similarities of tympanic membrane effusion images, tympanic membrane retraction images, and tympanic membrane perforation images that are greater than the minimum benchmark similarity are used as the disease image similarity, thereby improving the accuracy of the output results, improving the accuracy of the examination of the middle ear and inner ear of the examinee, and making it convenient for the examinee to examine his or her own middle ear and inner ear alone, so that the examinee can understand his or her own middle ear and inner ear.

[0207] For example, when the minimum benchmark similarity is 80%, the tympanic membrane effusion image similarity is 90%, the tympanic membrane retraction image similarity is 20%, and the tympanic membrane perforation image similarity is 30%, then only the tympanic membrane effusion image similarity is greater than the minimum benchmark similarity, so the tympanic membrane effusion image similarity is used as the disease image similarity.

[0208] The implementation principle of the above steps is as follows: judging by whether the similarity of the tympanic membrane effusion image, the similarity of the tympanic membrane retraction image, and the similarity of the tympanic membrane perforation image are all less than the preset minimum benchmark similarity, thereby judging whether the inner auditory canal detection image of the examined person, after being converted into a standard recognition image, has a high degree of similarity with the image detected in the inner auditory canal with the disease.

[0209] When the similarity rates of tympanic membrane effusion images, tympanic membrane retraction images, and tympanic membrane perforation images are all less than the preset minimum benchmark similarity rates, the normal image similarity rates and specific distinguishing point marking information are output to the terminal held by the person being examined.

[0210] When one or more of the tympanic membrane effusion image similarity, the tympanic membrane retraction image similarity, and the tympanic membrane perforation image similarity are greater than a preset minimum benchmark similarity, the one or more of the tympanic membrane effusion image similarity, the tympanic membrane retraction image similarity, and the tympanic membrane perforation image similarity greater than the minimum benchmark similarity are forward sorted, and the one or more of the tympanic membrane effusion image similarity, the tympanic membrane retraction image similarity, and the tympanic membrane perforation image similarity greater than the minimum benchmark similarity are output in sequence according to the forward sorting result as the disease image similarity, thereby improving the accuracy of the output result, improving the accuracy of the examination of the middle ear and inner ear of the examinee, and making it convenient for the examinee to examine his or her middle ear and inner ear alone, so that the examinee can understand his or her middle ear and inner ear.

[0211] Reference Fig. 9Based on the same inventive concept, an embodiment of the present invention provides an inner auditory canal intelligent self-detection system, comprising:

[0212] The acquisition module 1 is used to: acquire the inner auditory canal detection image information of the person being examined;

[0213] Identification module 2, used to: identify the inner auditory canal identification point from the inner auditory canal detection image information according to the preset inner auditory canal identification point features;

[0214] The first analysis module 3 is used to analyze and obtain standard recognition image information from the inner auditory canal detection image information according to the inner auditory canal recognition position point, the preset reference image information and the recognition reference point;

[0215] The second analysis module 4 is used to: analyze and output the normal image similarity rate and specific difference point marking information of the standard recognition image information and the normal inner auditory canal detection image information according to the comparison result between the standard recognition image information and the preset normal inner auditory canal detection image information;

[0216] The output module 5 is used to: take the normal image similarity and specific difference point marking information as the final detection result, and output the final detection result to the terminal held by the person being tested.

[0217] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. The specific working process of the system, device and unit described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0218] An embodiment of the present invention provides a computer storage medium storing a computer program that can be loaded by a processor and execute an inner auditory canal intelligent self-examination method.

[0219] Computer storage media include, for example, various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks or optical disks.

[0220] The above are all preferred embodiments of the present application, and are not intended to limit the protection scope of the present application. Any feature disclosed in this specification (including the abstract and drawings), unless otherwise stated, can be replaced by other equivalent or alternative features with similar purposes. That is, unless otherwise stated, each feature is only an example of a series of equivalent or similar features.

Claims

1. An inner auditory canal intelligent self-examination method, characterized in that: include: Acquire the inner ear canal detection image information of the inspected person; Identifying an inner auditory canal identification position point from the inner auditory canal detection image information according to a preset inner auditory canal identification point feature; Analyze and obtain standard recognition image information from the inner auditory canal detection image information according to the inner auditory canal recognition position point, the preset reference image information and the recognition reference point; According to the comparison result between the standard recognition image information and the preset normal inner ear canal detection image information, the normal image similarity rate and specific difference point marking information of the standard recognition image information and the normal inner ear canal detection image information are analyzed and output; The normal image similarity and specific difference point marking information are used as the final detection result, and the final detection result is output to the terminal held by the person being tested; Wherein, according to the inner auditory canal recognition position point, the preset reference image information and the recognition reference point, analyzing and obtaining the standard recognition image information from the inner auditory canal detection image information includes: Determine whether the number of inner auditory canal identification position points corresponding to the number of preset identification reference points is consistent; If yes, then obtaining edge position points of the reference image information and edge position points of the inner auditory canal detection image information; According to the edge position points of the reference image information and the edge position points of the inner auditory canal detection image information, the reference points and the inner auditory canal recognition position points are identified, and the recognition image adjustment information is obtained by analyzing the inner auditory canal detection image information, and the recognition image adjustment information is used as the standard recognition image information; If not, then according to the comparison relationship between the inner ear canal recognition position point, the inner ear canal missing recognition position point and the recognition reference point, analyze and obtain the inner ear canal missing recognition position point corresponding to the inner ear canal recognition position point and the recognition reference point; According to the correspondence between the number of inner auditory canal missing identification position points and the preset first adjustment scheme, analyzing and obtaining the first adjustment scheme corresponding to the number of inner auditory canal missing identification position points; According to the correspondence between the first adjustment scheme, the inner auditory canal detection image information and the standard recognition image information, analyzing and acquiring the standard recognition image information corresponding to the first adjustment scheme and the inner auditory canal detection image information; Among them, according to the edge position points of the reference image information and the edge position points of the inner auditory canal detection image information, the reference points and the inner auditory canal recognition position points are identified from the inner auditory canal detection image information to obtain the recognition image adjustment information, and the recognition image adjustment information is used as the standard recognition image information, including: Obtain identification reference points and inner auditory canal identification position points; The identification reference points and the inner auditory canal identification position points are respectively sorted in a forward direction, and the forward sorting is defined as the identification reference points being sorted in a clockwise order from the center of the reference image information to the outer circle, or the inner auditory canal identification position points being sorted in a clockwise order from the center of the inner auditory canal detection image information to the outer circle; According to the one-to-one correspondence between the positively sorted recognition reference points and the positively sorted inner auditory canal recognition position points, the inner auditory canal detection image information is analyzed and adjusted, and the recognition image adjustment information is output; The method further includes the following steps: after analyzing and outputting the normal image similarity rate and specific difference point marking information between the standard recognition image information and the normal inner auditory canal detection image information according to the comparison result between the standard recognition image information and the preset normal inner auditory canal detection image information, and before using the normal image similarity rate and specific difference point marking information as the final detection result and outputting the final detection result to the terminal held by the person being tested, which are as follows: Determine whether the normal image similarity is greater than a preset normal similarity reference value; If yes, the normal image similarity and specific difference point marking information are output to the terminal held by the inspected person; If the answer is no, then obtaining the disease inner ear canal detection image information, the disease inner ear canal detection image information including the tympanic membrane retraction inner ear canal detection image information, the tympanic membrane effusion inner ear canal detection image information and the tympanic membrane perforation inner ear canal detection image information; According to the comparison result between the standard recognition image information and the tympanic membrane effusion inner ear canal detection image information, the tympanic membrane effusion image similarity rate and specific difference point marking information between the standard recognition image information and the tympanic membrane effusion inner ear canal detection image information are output; According to the comparison result between the standard recognition image information and the tympanic membrane retraction inner ear canal detection image information, the similarity rate of the tympanic membrane retraction image and the specific difference point marking information between the standard recognition image information and the tympanic membrane retraction inner ear canal detection image information are output; According to the comparison result between the standard recognition image information and the tympanic membrane perforation inner ear canal detection image information, the similarity rate of the tympanic membrane perforation image and the specific difference point marking information between the standard recognition image information and the tympanic membrane perforation inner ear canal detection image information are output; The similarity rates of tympanic membrane effusion images, tympanic membrane retraction images, and tympanic membrane perforation images are used as the similarity rates of disease images, and the similarity rates of disease images and specific difference points are annotated to the terminal held by the person being examined; Among them, the similarity of tympanic membrane effusion image, tympanic membrane retraction image, and tympanic membrane perforation image as the disease image similarity includes: Determine whether the similarity of the tympanic membrane effusion image, the similarity of the tympanic membrane retraction image, and the similarity of the tympanic membrane perforation image are all less than a preset minimum benchmark similarity; If yes, the normal image similarity and specific difference point marking information are output to the terminal held by the inspected person; If not, then positive sorting is performed based on one or more of the similarity rates of tympanic membrane effusion images, tympanic membrane retraction images, and tympanic membrane perforation images that are greater than the minimum benchmark similarity rate, and positive sorting is defined as sorting from large to small values; According to the forward sorting result, one or more of the similarity rates of tympanic membrane effusion images, tympanic membrane retraction images, and tympanic membrane perforation images that are greater than the lowest benchmark similarity rate are output in sequence and used as the disease image similarity rate.

2. The inner auditory canal intelligent self-examination method according to claim 1, characterized in that: The step further includes one-to-one correspondence between the recognition reference points sorted in the positive direction and the inner auditory canal recognition position points sorted in the positive direction, analyzing and adjusting the inner auditory canal detection image information and outputting the recognition image adjustment information, which is specifically as follows: The distance between the first identification reference point and the edge position point of the reference image information is obtained as the reference distance value, and the distance between the first inner auditory canal identification position point and the edge position point of the inner auditory canal detection image information is obtained as the actual distance value; Determine whether the reference distance value is greater than the actual distance value; If not, an alarm message is output to the terminal held by the inspected person; If yes, differential image adjustment information is obtained from the inner auditory canal detection image information analysis according to the difference between the reference distance value and the actual distance value, and the differential image adjustment information is used as the standard recognition image information.

3. The inner auditory canal intelligent self-examination method according to claim 2, characterized in that: The difference image adjustment information is obtained by analyzing the inner auditory canal detection image information according to the difference between the reference distance value and the actual distance value, including: Obtain the difference between the reference distance value and the actual distance value and use it as the adjustment difference; Determine whether the adjustment difference is equal to a preset adjustment reference value; If yes, output the recognition image adjustment information, and use the recognition image adjustment information as the difference image adjustment information; If not, then according to the correspondence between the adjustment difference and the preset second adjustment solution, analyze and obtain the second adjustment solution corresponding to the adjustment difference; According to the correspondence between the second adjustment scheme, the inner auditory canal detection image information and the difference image adjustment information, the difference image adjustment information corresponding to the second adjustment scheme and the inner auditory canal detection image information is analyzed and acquired.

4. The inner auditory canal intelligent self-examination method according to claim 1, characterized in that: According to the correspondence between the number of inner auditory canal missing identification position points and the preset first adjustment scheme, analyzing and obtaining the first adjustment scheme corresponding to the number of inner auditory canal missing identification position points includes: Determine whether the number of inner auditory canal missing identification position points is less than a preset reference number; If not, an alarm message is output to the terminal held by the inspected person; If yes, determining whether the inner auditory canal missing identification position point is a preset adjustment angle position point; If yes, then according to the correspondence between the inner auditory canal missing identification position point and the preset adjustment angle scheme, an adjustment angle scheme corresponding to the inner auditory canal missing identification position point is analyzed and obtained, and the adjustment angle scheme is used as the first adjustment scheme; If not, an alarm message is output to the terminal held by the inspected person.

5. An inner auditory canal intelligent self-inspection system, using any inner auditory canal intelligent self-inspection method according to any one of claims 1 to 4, characterized in that: include: An acquisition module (1) is used to: acquire inner auditory canal detection image information of a person under examination; The recognition module (2) is used to: recognize the inner auditory canal recognition position point from the inner auditory canal detection image information according to the preset inner auditory canal recognition point features; A first analysis module (3) is used to analyze and obtain standard recognition image information from the inner auditory canal detection image information according to the inner auditory canal recognition position point, preset reference image information and recognition reference point; The second analysis module (4) is used to: analyze and output the normal image similarity rate and specific difference point marking information of the standard recognition image information and the normal inner auditory canal detection image information according to the comparison result between the standard recognition image information and the preset normal inner auditory canal detection image information; The output module (5) is used to: use the normal image similarity and specific difference point marking information as the final detection result, and output the final detection result to the terminal held by the person being detected.

6. A computer storage medium, characterized in that: A computer program is stored which can be loaded by a processor and execute the method according to any one of claims 1 to 4.

Images