Electronic laryngeal sound transmission point automatic positioning method

Abstract

The application discloses an automatic positioning method for a sound transmission point of an electronic laryngoscope, which comprises the following steps: collecting a head and neck image of a user of the electronic laryngoscope and extracting feature point distances, defining a positioning coordinate system and calibrating a top point of a carotid triangle area, calculating a position of an optimal sound transmission point and a posture vector coordinate of the electronic laryngoscope, and finally directly displaying the position of the optimal sound transmission point and the posture of the electronic laryngoscope in the image and giving specific coordinate values for reference of the user in the first use, and fine adjustment on the basis to achieve the best effect. The method can quickly find the use position and use direction of the electronic laryngoscope for the user to refer without early guidance and training. The algorithm is simple and easy to integrate into a mobile phone software and used with a front camera of the mobile phone.

Description

TECHNICAL FIELD

[0001] The present application relates to an automatic positioning method, in particular to an automatic positioning method of an electronic laryngeal sound transmission point. BACKGROUND

[0002] Electronic artificial larynx, also known as speech aid, is a speech recovery tool that uses electronic oscillation and electromagnetic vibration to replace vocal cord vibration to generate sound source, and the sound source is modulated through the sound channel of nasopharynx, mouth, teeth and lips to form language. It is commonly used for patients after laryngectomy or other failed voice surgery patients. Electronic larynx is a handheld semiconductor device with a plastic vibrating membrane, similar in size to an electric shaver. In order to produce sound, the end of the electronic larynx is placed on the optimal sound production point on the anterior side of the neck, and the sound is transmitted into the pharynx to form language. It is clean and easy to use, can talk for a long time and is easy to understand, does not require other care, and is basically suitable for any laryngectomee.

[0003] Due to different total laryngectomy methods, postoperative scar size, hyoid bone removal or post-radiation muscle tissue changes, neck muscles vary from person to person, so the optimal sound transmission point also varies from person to person. The optimal sound transmission point is usually the right hyoid angle posterior region, i.e. the carotid triangle region. The patient needs a long time of training and trial to find the optimal sound transmission point to achieve clear pronunciation, and it cannot be guaranteed that the optimal sound transmission point can be quickly found every time, thereby prolonging the adaptation process of the electronic larynx and reducing the convenience and effectiveness of use. SUMMARY

[0004] The present application aims to overcome the shortcomings of the prior art and provide an electronic laryngeal sound transmission point automatic positioning method with simple algorithm, which can quickly find the optimal use position and use direction of the electronic larynx for the user to refer.

[0005] The electronic laryngeal sound transmission point automatic positioning method of the present application comprises the following steps:

[0006] Step one, collect human head and neck samples, establish a sample group head and neck feature database, and the sample group head and neck feature database is used to store sample group front and right face images;

[0007] Step two, use digital image processing software to calibrate the coordinates of the three vertices of the carotid triangle region of the sample group in the sample group head and neck feature database, and then calculate the average values of the three vertices of the carotid triangle region, the specific steps are as follows:

[0008] First step, define the positioning coordinate system: the origin of the positioning coordinate system is the lowest point of the chin, the x-axis direction of the positioning coordinate system is the left side of the face direction, the y-axis direction is vertically upward, and the z-axis direction is the face direction;

[0009] Second step, calculate the average value of the coordinates of the three vertices of the carotid triangle of the sample group respectively, the specific steps are as follows:

[0010] 201, extract the head and neck front and right images of the sample group from the head and neck feature database of the sample group, and then calculate the average distance of each feature point of the head and neck of the sample group, the average distance of each feature point of the ith sample in the sample group includes the horizontal distance a between the outermost point O1 of the right ear contour and the outermost point O2 of the left ear contour i , the vertical distance b between the outermost point O1 of the right ear contour or the outermost point O2 of the left ear contour and the lowest point O of the chin i , the horizontal distance c between the outermost point O1 of the right ear contour and the lowest point O of the chin i (i = 1, 2, …, n), n represents the total number of the sample group; then the average distance of each feature point of the sample group is :

[0011]

[0012] 202, calculate the average coordinates of the three vertices of the carotid triangle of the sample group respectively The coordinates of the jth vertex D j,i (j = 1, 2, 3) of the carotid triangle of the ith sample in the sample group (i = 1, 2, …, n) are approximately estimated by the following formula:

[0013] The coordinates of the first vertex D 1,i : (x D1,i , y D1,i , z D1,i ),

[0014] The coordinates of the second vertex D 2,i : (x D2,i , y D2,i , z D2,i ),

[0015] The coordinates of the third vertex D 3,i : (x D3,i , y D3,i , z D3,i ),

[0016] The average coordinates of the three vertices of the sample group (j = 1, 2, 3) are:

[0017]

[0018] Step three, calculate the best sound transmission point position and electronic throat posture for the current electronic throat user, the steps are as follows:

[0019] 301, using a digital image processing software to collect the front image and the right image of the current electronic larynx user, to obtain the horizontal distance a* between the outermost point O1 of the right ear contour and the outermost point O2 of the left ear contour of the current electronic larynx user, the vertical distance b* from the outermost point O1 of the right ear contour or the outermost point O2 of the left ear contour to the lowest point O of the chin, and the horizontal distance c* from the outermost point O1 of the right ear contour to the lowest point O of the chin;

[0020] 302, the matching proportion coefficient μ is calculated according to the following formula:

[0021]

[0022] 303, the coordinates of the three vertices of the carotid triangle area of the current electronic larynx user are calculated as:

[0023]

[0024] 304, the centroid D of the carotid triangle area is defined as the best sound transmission point, and the coordinates of D are calculated as:

[0025]

[0026] Electronic larynx posture direction The unit direction vector coordinates are represented as:

[0027]

[0028] Step four, image display and automatic prompting in the digital image collection software, the steps are:

[0029] According to the coordinates of the best sound transmission point of step 304 and the electronic larynx posture direction vector coordinates, the position of the best sound transmission point and the electronic larynx posture are directly displayed in the front image and the right image of the user collected in step 301, and the specific coordinate values are given, so as to provide a reference for the user to use for the first time, and to fine-tune on this basis to achieve the best effect.

[0030] Compared with the prior art, the present application has the following beneficial effects:

[0031] The method of the present application can quickly find the best use position and use direction of the electronic larynx for the user to refer without prior guidance and training. The algorithm is simple and easy to integrate into mobile phone software and cooperate with mobile phone front camera. BRIEF DESCRIPTION OF DRAWINGS

[0032] In order to more clearly illustrate the technical solutions in the examples of the present application or the prior art, the accompanying drawings needed to be used in the embodiments or prior art description will be briefly introduced as follows. The accompanying drawings in the following description are only one embodiment of the present application, and other accompanying drawings can be obtained by those skilled in the art without creative effort on the premise that the accompanying drawings do not pay creative effort.

[0033] Figure 1 is a front image of an electronic laryngeal user involved in an electronic laryngeal sound transmission point automatic positioning method of the present application;

[0034] Figure 2 is Figure 1 a right image of an electronic laryngeal user shown in the figure;

[0035] Figure 3 is an electronic laryngeal sound transmission point automatic positioning method of the present application. DETAILED DESCRIPTION

[0036] The present application will be described in detail below in combination with specific embodiments and accompanying drawings.

[0037] An electronic laryngeal sound transmission point automatic positioning method of the present application, as shown in the accompanying drawings, comprises the following steps:

[0038] Step one, collect human head and neck samples, and establish a sample group head and neck feature database, wherein the sample group head and neck feature database is used to store sample group head and neck front and right images;

[0039] Step two, use digital image processing software to calibrate the coordinates of the three vertices of the carotid triangle area of the sample group in the sample group head and neck feature database, and then calculate the average values of the three vertices of the carotid triangle area, and the specific steps are as follows:

[0040] First step, define the positioning coordinate system: the origin of the positioning coordinate system is the lowest point of the chin, the x-axis direction of the positioning coordinate system is the left side of the face direction, the y-axis direction is vertically upward, and the z-axis direction is the face direction.

[0041] Second step, calculate the average values of the coordinates of the three vertices of the carotid triangle area of the sample group, and the specific steps are as follows:

[0042] 201, extract the head and neck front and right images of the sample group from the sample group head and neck feature database, and then calculate the average distances of each feature point of the head and neck of the sample group, wherein the average distance of each feature point of the i-th sample in the sample group includes the horizontal distance a between the outermost point O1 of the right ear contour and the outermost point O2 of the left ear contour i , the vertical distance b between the outermost point O1 of the right ear contour or the outermost point O2 of the left ear contour and the lowest point O of the chin i , and the horizontal distance c between the outermost point O1 of the right ear contour and the lowest point O of the chini (i = 1, 2, …, n), n represents the total number of sample population; the average distance of each feature point of the sample population For

[0043]

[0044] 202, respectively, calculate the average coordinates of the three vertices of the carotid triangle of the sample population (j = 1, 2, 3). The coordinates of the jth vertex D j,i (j = 1, 2, 3)(i = 1, 2, …, n) of the carotid triangle of the ith sample in the sample population are approximately estimated by using the following formula according to the definition in 《Human Anatomy》(Guo Zhikun, Zang Weidong, Henan Science and Technology Press, published in 2015.08, Chapter 11, Section 3, page 212):

[0045] The coordinates of the first vertex D 1,i : (x D1,i , y D1,i , z D1,i ),

[0046] The coordinates of the second vertex D 2,i : (x D2,i , y D2,i , z D2,i ),

[0047] The coordinates of the third vertex D 3,i : (x D3,i , y D3,i , z D3,i ),

[0048] The average coordinates of the three vertices of the sample population (j = 1, 2, 3) are respectively:

[0049]

[0050] Step three, calculate the best sound transmission point position and electronic larynx posture for the current electronic larynx user, the steps are:

[0051] 301, use digital image processing software to collect the front and right images of the head and neck of the current electronic larynx user, obtain the horizontal distance a* between the outermost point O1 of the right ear contour and the outermost point O2 of the left ear contour, the vertical distance b* from the right ear contour outermost point O1 or the left ear contour outermost point O2 to the lowest point O of the chin, and the horizontal distance c* from the right ear contour outermost point O1 to the lowest point O of the chin.

[0052] 302, the matching proportion coefficient μ is calculated according to the following formula:

[0053]

[0054] 303, the coordinates of the three vertices of the carotid triangle of the current electronic laryngoscope user are calculated as:

[0055]

[0056] 304, the centroid D of the carotid triangle is defined as the optimal sound transmission point, and the coordinates of D are calculated as:

[0057]

[0058] Electronic laryngoscope posture direction The unit directional vector coordinates of the electronic laryngoscope posture direction are represented as:

[0059]

[0060] Step four, image display and automatic prompting in digital image acquisition software, the steps are:

[0061] According to the coordinates of the optimal sound transmission point and the directional vector coordinates of the electronic laryngoscope posture direction in step 304, the optimal sound transmission point position and the electronic laryngoscope posture are directly displayed in the front and right images of the user's head and neck collected in step 301, and specific coordinate values are given for the user to refer to when using for the first time, and to fine-tune on this basis to achieve the best effect.

[0062] The algorithm of the present application can be developed into a mobile phone software, which can cooperate with the front camera of the mobile phone to automatically collect and analyze images online, recognize the position and posture of the user's handheld electronic laryngoscope, and give the best prompt.

[0063] The above description of the embodiments is for the convenience of those skilled in the art to understand and apply the present application. Those skilled in the art can easily make various modifications to these embodiments, and apply the general principles described herein to other embodiments without creative labor. Therefore, the present application is not limited to the embodiments herein, and any improvements and modifications made by those skilled in the art based on the disclosure of the present application without departing from the scope of the present application should be within the scope of protection of the present application.

Claims

1. An automatic positioning method for electronic throat sound transmission points, characterized in that... Includes the following steps: Step 1: Collect human head and neck samples and establish a sample group head and neck feature database. The sample group head and neck feature database is used to store front and right-side images of the sample group's head and neck. Step 2: Use digital image processing software to calibrate the coordinates of the three vertices of the carotid triangle region of the sample population in the head and neck feature database, and then calculate the average value of the three vertices of the carotid triangle region. The specific steps are as follows: The first step is to define the positioning coordinate system: the origin of the positioning coordinate system is the lowest point of the chin, the x-axis is to the left of the facing direction, the y-axis is vertically upward, and the z-axis is the facing direction. The second step is to calculate the average coordinates of the three vertices of the carotid triangle region for each sample group. The specific steps are as follows:

201. Extract the frontal and right-side images of the head and neck of the sample group from the head and neck feature database. Then calculate the average distance of each feature point at the head and neck of the sample group. The average distance of each feature point of the i-th sample in the sample group includes the horizontal distance a between the outermost point O1 of the right ear contour and the outermost point O2 of the left ear contour. i The vertical distance b from the outermost point O1 of the right ear contour or the outermost point O2 of the left ear contour to the lowest point O of the chin. i The horizontal distance c between the outermost point O1 of the right ear outline and the lowest point O of the chin. i , i = 1, 2, ..., n; n represents the total number of feature points in the sample group; then the average distance between each feature point in the sample group is... for:

202. Calculate the average coordinates of the three vertices of the carotid triangle region in the sample population. The j-th vertex D of the three vertices of the carotid triangle region of the i-th sample in the aforementioned sample group. j,i The coordinates of (j=1,2,3)(i=1,2,…,n) can be approximately estimated using the following formula: The first vertex D 1,i Coordinates: (x D1,i ,y D1,i ,z D1,i ), The second vertex D 2,i Coordinates: (x D2,i ,y D2,i ,z D2,i ), The third vertex D 3,i Coordinates: (x D3,i ,y D3,i ,z D3,i ), y D3,i =0, The average coordinates of the three vertices of the sample population They are respectively: Step 3: Calculate the optimal sound transmission point position and electronic larynx posture for the current electronic larynx user. The steps are as follows:

301. Use digital image processing software to acquire the frontal and right-side images of the head and neck of a current electronic larynx user, and obtain the horizontal distance a* between the outermost point O1 of the right ear contour and the outermost point O2 of the left ear contour of the current electronic larynx user, the vertical distance b* from the outermost point O1 of the right ear contour or the outermost point O2 of the left ear contour to the lowest point O of the chin, and the horizontal distance c* from the outermost point O1 of the right ear contour to the lowest point O of the chin. 302, calculate the matching ratio coefficient μ according to the following formula: 303, calculate the coordinates of the three vertices of the carotid triangle region of the current electronic larynx user as follows:

304. If the centroid D of the carotid triangle is defined as the optimal sound transmission point, then the coordinates of D are calculated as follows: Electronic throat attitude direction The unit direction vector coordinates are represented as: Step four: Display the image and provide automatic prompts in the digital image acquisition software. The steps are as follows: Based on the optimal sound transmission point coordinates and the electronic larynx posture direction vector coordinates from step 304, the optimal sound transmission point position and electronic larynx posture are directly displayed in the front and right head and neck images of the user acquired in step 301, along with specific coordinate values, for the user's reference when using it for the first time, and for fine-tuning to achieve the best effect.

Images