Method for stabilizing identification of acupoints on back of human body and intelligent terminal

Abstract

The application discloses a method for stably identifying acupoints on the back of a human body and an intelligent terminal, and relates to the technical field of acupoint identification. The method comprises the following steps: acquiring an image of the back of a user and acquiring positioning coordinates of a reference acupoint, calculating the proportion of the human body according to the reference acupoint; dividing the reference acupoint into a plurality of groups, determining a reference straight line according to a representative point in each group, and acquiring a spinal alignment identification line; calculating the specific positions of other acupoints according to the proportion of the human body and the spinal alignment identification line. The application acquires an image of the back of a user, labels the coordinates of a reference acupoint, calculates the representative points of a plurality of groups divided by the reference acupoint to determine the reference straight line of the plurality of groups, and then generates a spinal alignment identification line, thereby determining the positions of other acupoints in combination with the proportion of the human body and the spinal alignment identification line. The application comprehensively considers the spinal alignment and the proportion of the human body, realizes accurate labeling of acupoints and improves the identification efficiency, and also ensures the accuracy of the positioning result and the physiological reasonableness.

Description

Technical Field

[0001] This invention relates to the field of robot vision recognition technology, and in particular to a method and intelligent terminal for stably recognizing acupoints on the human back. Background Technology

[0002] With the continuous development of TCM diagnostic and treatment techniques, the accuracy and efficiency of acupoint location are receiving increasing attention from the medical community. Especially in traditional treatment methods such as acupuncture, massage, and moxibustion, the precise location of acupoints on the back directly affects treatment efficacy and patient experience. The back, as an important therapeutic area of ​​the body, contains as many as 95 key acupoints. These acupoints are distributed along important meridians such as the Governing Vessel and Bladder Meridian, and are not only closely related to the functions of the internal organs but also play a vital role in disease prevention and treatment. Accurate acupoint location not only improves treatment effectiveness but also reduces medical risks such as incorrect acupuncture and moxibustion, and is of great significance for TCM teaching, clinical research, and standardization.

[0003] In existing technologies, the location of acupoints on the back mainly relies on physicians to measure them using the bone measurement method. This method has problems such as strong subjectivity, low operational efficiency, and lack of standardization. When multiple acupoints need to be located, the location results vary between different physicians. Although there are existing technologies that use machine vision to identify acupoints, such as the meridian acupoint massage method based on deep learning disclosed in CN115429683A, existing machine recognition cannot locate acupoints specifically for different users' body shapes, resulting in inaccurate acupoint location.

[0004] Therefore, existing technologies still need to be improved and developed. Summary of the Invention

[0005] To address the problems of inefficiency, lack of standardization, and significant differences in positioning results among different physicians when locating multiple acupoints on a user's back using existing technologies, which rely on subjective measurements by physicians, and the inaccuracy of acupoint positioning caused by using machine vision to identify acupoints, this invention proposes a method and intelligent terminal for stable identification of acupoints on the human back.

[0006] This invention is achieved through the following technical solution:

[0007] A method for reliably identifying acupoints on the human back, wherein the method includes:

[0008] Obtain the back image of the current user, obtain the positioning coordinates of the reference acupoints based on the back image, and calculate the body proportions of the current user based on the positioning coordinates of the reference acupoints.

[0009] The reference acupoints are divided into several groups containing left and right symmetrical reference acupoints. Representative points on the left and right sides of each group are calculated based on the positioning coordinates. A reference straight line is determined based on the representative points.

[0010] Obtain the spine alignment marker line for the current user based on the reference straight line;

[0011] The specific locations of other acupoints are calculated based on the human body proportions and the spinal alignment markings.

[0012] The method for stably identifying acupoints on the human back, wherein calculating representative points on the left and right sides of each group based on the positioning coordinates includes:

[0013] Calculate the representative point P in each of the aforementioned groups. l (x l ,y l ) and P r (x r ,y r );

[0014] The representative point P l (x l ,y l () represents the mean value of several acupoints on the left side of the group;

[0015] The representative point P r (x r ,y r () represents the mean value of several acupoints on the right side of the group.

[0016] The method for stably identifying acupoints on the human back, wherein determining the reference straight line based on the representative point includes:

[0017] Based on the representative point P in several of the aforementioned groups l (x l ,y l ) and P r (x r ,y r Calculate the slope k and intercept b of the reference line L1 for the corresponding group, and determine the reference line L1 based on the slope k and intercept b;

[0018] The formula for calculating the slope k is: k = (y r -y l ) / (x r -x l );

[0019] The formula for calculating the intercept b is: b = y l -k*x l .

[0020] The method for stably identifying acupoints on the human back, wherein obtaining the spinal alignment marker line of the current user based on the reference straight line includes:

[0021] The slope k2 of the spinal alignment is calculated based on several reference straight lines L1, and the spinal alignment marker line is generated at the center point of the reference straight lines L1 based on the slope k2.

[0022] The slope k2 of the spine alignment marking line is calculated using the formula: k2 = -1 / k.

[0023] The method for stably identifying acupoints on the human back, wherein calculating the specific locations of other acupoints based on the human body proportions and the spinal alignment marker line includes:

[0024] Calculate the basic scale d, and determine the specific locations p of other acupoints based on the basic scale d. new ;

[0025] The basic scale d is the highest point p in the group. max and the lowest point p min The distance between them;

[0026] The formula for calculating the basic scale d is:

[0027] The specific locations of the other acupoints p new The calculation formula is:

[0028] x new =x min +t*d*cos(arctan(k2));

[0029] y new =y min +t*d*sin(arctan(k2)).

[0030] The method for stably identifying acupoints on the human back, wherein acquiring a back image of the current user and obtaining the location coordinates of the reference acupoints based on the back image includes:

[0031] The trained model is used to process the current user's back image;

[0032] Before processing the back image of the current user using the trained model, the following steps are also included:

[0033] A training model is constructed, the training model including a human back acupoint dataset, the human back acupoint dataset including several human back images with coordinate data of the reference acupoints.

[0034] The method for stably identifying acupoints on the human back, wherein the human back acupoint dataset further includes augmented data;

[0035] The enhanced data is an image obtained by randomly rotating, scaling, and brightness-processing several pairs of images of the human back.

[0036] The method for stably identifying acupoints on the human back, wherein dividing the reference acupoints into several groups including bilaterally symmetrical reference acupoints includes:

[0037] Grouped according to the location of the reference acupoints in the back image;

[0038] The groups include the shoulder area group, the mid-back area group, and the waist area group;

[0039] The shoulder area group includes eight acupoints symmetrically located on both sides: Jianzhongyu, Jianwaiyu, Bingfeng, and Tianzong.

[0040] The central back area group includes six acupoints symmetrically placed on both sides: Geshu, Hunmen, and Sanjiaoshu.

[0041] The lumbar region group includes 12 acupoints symmetrically placed on both sides: Guanyuanshu, Pangguanshu, Baihuanshu, Zhibian, Huiyang, and Jingmen.

[0042] The method for stably identifying acupoints on the human back, wherein dividing the reference acupoints into several groups including bilaterally symmetrical reference acupoints further includes:

[0043] Alternatively, grouping can be based on the meridian connections of the reference acupoints in the back images;

[0044] Alternatively, grouping based on the functional attributes of the reference acupoints in the back image;

[0045] Alternatively, grouping based on the recognition confidence of the reference acupoints in the back images.

[0046] A smart terminal, comprising a memory, a processor, and a program for stably identifying acupoints on the back of the human body stored in the memory and executable on the processor, wherein when the processor executes the program for stably identifying acupoints on the back of the human body, the method for stably identifying acupoints on the back of the human body as described above is implemented.

[0047] The smart terminal also includes a display, which can simultaneously display at least two display pages. One display page is used to display the back image of the current user, and the other display page is used to display the back image of the current user after marking the reference acupoints and other acupoints.

[0048] The beneficial effects of this invention are as follows: By acquiring an image of the user's back, this invention accurately marks the coordinates of reference acupoints, divides these reference acupoints into several groups, calculates representative points for each group, determines a reference straight line based on the representative points, and then generates a spinal alignment marker line. Combining the spinal alignment marker line with human body proportions, this invention can accurately determine the specific location of acupoints. Compared with existing technologies, this invention achieves accurate acupoint marking by comprehensively considering spinal alignment and human body proportions. This not only significantly increases the number of identifiable acupoints and improves recognition efficiency but also ensures the accuracy and physiological rationality of the positioning results. Attached Figure Description

[0049] Figure 1 This is a flowchart of the method for stably identifying acupoints on the human back according to the present invention;

[0050] Figure 2 This is a schematic diagram of the current user's back image in the method for stably identifying acupoints on the human back according to the present invention;

[0051] Figure 3 This is a schematic diagram of the back image after the reference acupoints are marked in the method for stably identifying acupoints on the human back according to the present invention;

[0052] Figure 4 This is a schematic diagram of the back image after gas acupoint marking in the method for stably identifying acupoints on the human back according to the present invention;

[0053] Figure 5 This is a schematic diagram of the display page of the display in the smart terminal of the present invention;

[0054] Figure 6 This is a block diagram illustrating the internal structure principle of the smart terminal of this invention. Detailed Implementation

[0055] To make the objectives, technical solutions, and effects of this invention clearer and more explicit, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0056] It should be noted that if the embodiments of the present invention involve directional indicators (such as up, down, left, right, front, back, etc.), the directional indicators are only used to explain the relative positional relationship and movement of the components in a certain specific posture (as shown in the figure). If the specific posture changes, the directional indicators will also change accordingly.

[0057] Furthermore, if the embodiments of this invention involve descriptions such as "first" or "second," these descriptions are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, features defined with "first" or "second" may explicitly or implicitly include at least one of those features. Additionally, the technical solutions of the various embodiments can be combined with each other, but this must be based on the ability of those skilled in the art to implement them. If the combination of technical solutions is contradictory or impossible to implement, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection claimed by this invention.

[0058] In existing technologies, the location of acupoints on the back mainly relies on physicians to measure them using the bone measurement method. This method has problems such as strong subjectivity, low operational efficiency, and lack of standardization. When multiple acupoints need to be located, the location results vary between different physicians. Although there are existing technologies that use machine vision to identify acupoints, such as the meridian acupoint massage method based on deep learning disclosed in CN115429683A, existing machine recognition cannot locate acupoints specifically for different users' body shapes, resulting in inaccurate acupoint location.

[0059] To address the aforementioned problems in the existing technology, this invention provides a method for stably identifying acupoints on the human back, such as... Figure 1 As shown, this method for stably identifying acupoints on the human back includes:

[0060] S100. Obtain the back image of the current user, obtain the positioning coordinates of the reference acupoints based on the back image, and calculate the body proportions of the current user based on the positioning coordinates of the reference acupoints.

[0061] S200. Divide the reference acupoints into several groups containing left and right symmetrical reference acupoints, calculate representative points on the left and right sides of each group according to the positioning coordinates, and determine the reference straight line according to the representative points.

[0062] S300: Obtain the spine orientation marker line of the current user based on the reference straight line;

[0063] S400. Calculate the specific locations of other acupoints based on the human body proportions and the spinal alignment marking lines.

[0064] In this embodiment, the reference acupoints are acupoints on the back of the human body located in easily accessible areas. This is determined after acquiring an image of the user's back (e.g., ...). Figure 2 After (as shown), the specific location of the reference acupoint can be determined based on the user's back image features, such as the characteristic distribution of the back bones and the characteristic distribution of muscle trends, for example... Figure 3As shown, in one specific embodiment, the reference acupoints include the left and right symmetrical points of acupoints such as Jianzhongshu, Jianwaishu, Bingfeng, Tianzong, Geshu, Hunmen, Sanjiaoshu, Jingmen, Guanyuanshu, Pangguanshu, Baihuanshu, Zhibian, and Huiyang. These acupoints are not only commonly used and safe massage acupoints in clinical practice, but also acupoints that are easy to distinguish in images. Therefore, it is easy to mark the coordinates of the above-mentioned reference acupoints in the back image, that is, to obtain the positioning coordinates of the reference acupoints.

[0065] Meanwhile, after the coordinates of the reference acupoints are marked and determined, the current user's body proportions can be calculated by processing several coordinates. Body proportions include, but are not limited to, the proportions of height, shoulder width, back width, and pelvic width. These proportions provide key parameters for the subsequent calculation of the specific locations of other acupoints, thereby avoiding the influence of the current user's body shape conditions such as weight or height when marking other acupoints.

[0066] Furthermore, such as Figure 3 As shown, since the acupoints on the back of the human body are symmetrically distributed along the spine, the above-mentioned reference acupoints can be divided into several groups containing symmetrical reference acupoints. Based on the marked positioning coordinates, the representative points on the left and right sides of each group are calculated. The representative points are obtained by averaging multiple positioning coordinates in the group and can represent the distribution of several reference acupoints in the group for the current user. At the same time, since two points determine a straight line, after calculating the representative points on the left and right sides of each group, the reference straight line of each group can be obtained by connecting the representative points on the left and right sides.

[0067] Furthermore, since acupoints are symmetrically distributed along the spine, after obtaining the baseline line, the spinal direction marker line can be determined through the baseline line. Thus, using the spinal direction marker line as a basis, combined with the calculated body proportions of the current user and the coordinates of the calculated representative points, as well as the traditional bone measurement theory, it is possible to calculate the specific location of other acupoints.

[0068] This invention acquires an image of the user's back, accurately marks the coordinates of reference acupoints, divides these acupoints into several groups, calculates representative points for each group, determines a baseline line based on these representative points, and then generates a spinal alignment marker line. By combining the spinal alignment marker line with human body proportions, this invention can accurately determine the specific location of acupoints. Compared with existing technologies, this invention achieves precise acupoint marking by comprehensively considering spinal alignment and human body proportions (e.g., ...). Figure 4 (As shown). This not only significantly increases the number of identifiable acupoints and improves identification efficiency, but also ensures the accuracy and physiological rationality of the positioning results.

[0069] In another possible embodiment of the present invention, the above-mentioned calculation of representative points on the left and right sides of each group based on the positioning coordinates includes:

[0070] S210. Calculate the representative points P in each of the aforementioned groups. l (x l ,y l ) and P r (x r ,y r );

[0071] Among them, point P represents l (x l ,y l P represents the mean value of several acupoints on the left side of the group; the representative point is P. r (x r ,y r () represents the mean value of several acupoints on the right side of the group.

[0072] In one specific embodiment, the mean points are calculated for the left-side acupoints (such as the left shoulder sac shu and left shoulder wai shu) and right-side acupoints (such as the right shoulder shu and right shoulder wai shu) in the above group, respectively, to obtain two representative points P on the left and right sides. l (x l ,y l ) and P r (x r ,y r By calculating the mean points of acupoints on both sides of each group, the distribution of acupoints within that group can be more accurately reflected. When calculating the mean points, the location coordinates of each acupoint can be considered and weighted to obtain more precise representative point coordinates. This method not only improves the accuracy of acupoint location but also helps in the subsequent accurate determination of baseline lines and spinal alignment markers based on these representative points.

[0073] Based on the above, two representative points P on the left and right are obtained. l (x l ,y l ) and P r (x r ,y r After that, the reference line corresponding to the group can be determined by using two points to determine a straight line. The above determination of the reference line based on the representative points includes:

[0074] S220, Based on the representative point P in the plurality of said groups l (x l ,y l ) and P r (x r ,y rCalculate the slope k and intercept b of the reference line L1 for the corresponding group, and determine the reference line L1 based on the slope k and intercept b;

[0075] The formula for calculating the slope k is: k = (y r -y l ) / (x r -x l The formula for calculating the intercept b is: b = y l -k*x l .

[0076] The baseline line L1 can be drawn using the slope k and the intercept b. This allows us to draw the baseline line L1 for all groups. These baseline lines not only reflect the distribution of acupoints on the back of the human body, but also provide an important basis for determining the spinal alignment marker line.

[0077] Specifically, obtaining the current user's spine alignment marker line based on the reference straight line includes:

[0078] S310. Calculate the slope k2 of the spinal direction based on a plurality of reference straight lines L1, and generate the spinal direction identification line at the center point of the reference straight line L1 based on the slope k2.

[0079] According to human anatomical characteristics, the direction of the spine should be perpendicular to the reference straight line, and the formula for calculating the slope k2 of the spine direction is: k2=-1 / k.

[0080] It should be noted that, in the above embodiment, the baseline line L1 of each group was obtained. Therefore, the slope k2 of the spinal orientation marker line corresponding to a single group can be obtained through the above calculation formula. After obtaining the spinal orientation marker lines corresponding to all groups, the parts of the spinal orientation marker lines corresponding to each group can be processed to integrate several spinal orientation marker lines into one spinal orientation marker line. The integrated spinal orientation marker line can more accurately reflect the actual orientation of the current user's spine, providing a key reference for subsequent acupoint positioning.

[0081] Furthermore, the calculation of the specific locations of other acupoints based on the aforementioned human body proportions and the spinal alignment marking lines includes:

[0082] S410. Calculate the basic scale d, and determine the specific locations p of other acupoints based on the basic scale d. new ;

[0083] Wherein, the basic scale d is the highest point p in the group. max and the lowest point p min The distance between them;

[0084] The formula for calculating the basic scale d is: The basic scale d is the benchmark used to determine the location of other acupoints based on human body proportions;

[0085] Based on the above steps, the specific locations p of other acupoints are finally calculated. new The calculation formula is:

[0086] x new =x min +t*d*cos(arctan(k2));

[0087] y new =y min +t*d*sin(arctan(k2)).

[0088] Where t is a proportional coefficient determined according to the traditional theory of bone measurement;

[0089] Where cos(arctan(k2)) is the projected distance of the x-coordinate of other acupoints relative to the spinal alignment marker line; sin(arctan(k2)) is the projected distance of the y-coordinate of other acupoints relative to the spinal alignment marker line.

[0090] 't' represents the relative proportion between other acupoints and the representative point. This proportion can be determined based on the bone measurement method in traditional Chinese medicine theory. By analyzing the proportional relationships of different body parts, the relative positional relationships between acupoints are obtained. By combining human body proportions, spinal alignment lines, and traditional bone measurement theory, this invention can achieve precise location of other acupoints on the back. This method not only improves the accuracy and efficiency of acupoint location but also provides more reliable technical support for traditional Chinese medicine therapies such as massage and acupuncture. Furthermore, the embodiments of this invention may further include preprocessing steps for the user's back image, such as noise reduction and contrast enhancement, to improve the accuracy and stability of acupoint recognition. Simultaneously, this invention can further improve the accuracy and applicability of acupoint recognition by continuously optimizing the algorithm and model to adapt to different users' body shapes and back characteristics.

[0091] In another possible embodiment of the present invention, in order to achieve a more accurate annotation of the positioning coordinates of the reference acupoints when obtaining the positioning coordinates of the reference acupoints based on the back image in the above-mentioned S100, the method of obtaining the back image of the current user and obtaining the positioning coordinates of the reference acupoints based on the back image in the present invention includes:

[0092] S110. Process the back image of the current user using the trained model;

[0093] Before processing the current user's back image using the trained model, the following steps are also included:

[0094] S10. Construct a training model, wherein the training model includes a human back acupoint dataset, and the human back acupoint dataset includes several human back images with coordinate data of the reference acupoints.

[0095] This invention first constructs a professional dataset of back acupoints. This was achieved by collecting over 5000 images of human backs of different body types and under different lighting conditions, and then inviting professional traditional Chinese medicine practitioners to annotate these images. For example... Figure 3 As shown, the annotations include 26 benchmark acupoints, which are anatomically divided into three regions: the shoulder region (8 points symmetrically located on both sides, including Jianzhongshu, Jianwaishu, Bingfeng, and Tianzong); the mid-back region (6 points symmetrically located on both sides, including Geshu, Hunmen, and Sanjiaoshu); and the lumbar region (12 points symmetrically located on both sides, including Guanyuanshu, Pangguangshu, Baihuanshu, Zhibian, Huiyang, and Jingmen). To ensure annotation quality, multiple quality control mechanisms were employed, including cross-validation by multiple experts, data cleaning, and outlier detection.

[0096] During the model training phase, this invention employs the YOLOv8 model to identify 26 benchmark acupoints. The training process begins with pre-training on the COCO dataset to acquire basic feature extraction capabilities, followed by fine-tuning on a self-built back acupoint dataset.

[0097] Furthermore, the aforementioned human back acupoint dataset also includes augmented data, which consists of images obtained by randomly rotating, scaling, and brightness-processing several pairs of human back images.

[0098] The purpose of the above-mentioned augmented data settings is to improve the generalization ability of the model training. In addition to using the above-mentioned augmented data, the imbalance of samples is effectively solved by using Focal Loss as the loss function. After continuous optimization and verification, the recognition accuracy of the model on the test set is further improved.

[0099] Based on the above-mentioned method of using a training model to obtain the location coordinates of reference acupoints from a user's back image, and by dividing the reference acupoints into groups to calculate representative points, reference lines, and spinal direction markers, the present invention can effectively improve the accuracy of identifying reference acupoints and other acupoints.

[0100] There are various specific ways to divide the reference acupoints into several groups that include bilaterally symmetrical reference acupoints. In one specific embodiment, the reference acupoints can be grouped according to their location in the back image, specifically into a shoulder region group, a mid-back region group, and a waist region group; for example... Figure 3As shown, the shoulder area group includes 8 acupoints symmetrically arranged on both sides: Jianzhongshu, Jianwaishu, Bingfeng, and Tianzong; the back mid-area group includes 6 acupoints symmetrically arranged on both sides: Geshu, Hunmen, and Sanjiaoshu; and the waist area group includes 12 acupoints symmetrically arranged on both sides: Guanyuanshu, Pangguangshu, Baihuanshu, Zhibian, Huiyang, and Jingmen.

[0101] In other possible implementations, the above-mentioned division of the reference acupoints into several groups including bilaterally symmetrical reference acupoints can also be carried out in other ways, for example:

[0102] The acupoints in the back images can be grouped according to their meridian connections. According to Traditional Chinese Medicine (TCM) meridian theory, specific meridian connections exist between acupoints in the human body. Therefore, acupoints with the same or similar meridian connections can be grouped together. This grouping method allows for a deeper exploration and utilization of TCM meridian theory, further improving the accuracy and scientific rigor of acupoint location.

[0103] The acupoints can also be grouped according to their functional attributes in the back images. Human acupoints not only have specific anatomical locations but also carry different functional attributes. For example, some acupoints have significant effects on relieving neck and shoulder pain and improving blood circulation. Therefore, acupoints with the same or similar functional attributes can be grouped together. This grouping method can more comprehensively reflect the characteristics and functions of acupoints, providing more precise guidance for subsequent acupoint location and treatment.

[0104] The acupoints can also be grouped according to their recognition confidence in the back image; that is, acupoints with higher recognition confidence are grouped into one group, and acupoints with lower recognition confidence are grouped into another group. This grouping method allows for targeted processing and analysis of acupoints with different confidence levels, further improving the stability and reliability of acupoint recognition.

[0105] When implementing this invention, a suitable grouping method can be selected according to specific needs and scenarios to achieve the best acupoint recognition effect. This invention makes full use of the known acupoint location information and determines the key reference line by the overall distribution characteristics of acupoints within the group. Secondly, by establishing the vertical relationship, the spinal direction is accurately grasped, which is crucial for locating other acupoints. Finally, by using the projection distance as the basic scale, the accuracy of the calculation is ensured, and it can adapt to individual differences in different body types.

[0106] Based on the above embodiments, the present invention also provides a smart terminal, the principle block diagram of which can be as follows: Figure 6As shown, the smart terminal includes a processor, memory, network interface, and display screen connected via a system bus. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The network interface is used to communicate with external terminals via a network connection. When executed by the processor, the computer program implements a method for stably identifying acupoints on the human back.

[0107] Those skilled in the art will understand that Figure 6 The block diagram shown is merely a partial structural diagram related to the present invention and does not constitute a limitation on the smart terminal to which the present invention is applied. A specific smart terminal may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0108] In one embodiment, a smart device is provided, including a memory and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by one or more processors. The one or more programs include instructions for performing the following operations:

[0109] Obtain the back image of the current user, obtain the positioning coordinates of the reference acupoints based on the back image, and calculate the body proportions of the current user based on the positioning coordinates of the reference acupoints.

[0110] The reference acupoints are divided into several groups containing left and right symmetrical reference acupoints. Representative points on the left and right sides of each group are calculated based on the positioning coordinates. A reference straight line is determined based on the representative points.

[0111] Obtain the spine alignment marker line for the current user based on the reference straight line;

[0112] The specific locations of other acupoints are calculated based on the human body proportions and the spinal alignment markings.

[0113] In addition, such as Figure 5 As shown, the smart terminal also includes a display capable of simultaneously displaying at least two screens. One screen displays the current user's back image, and the other screen displays the current user's back image with reference acupoints and other acupoints marked. This invention, through its dual-window side-by-side display design, shows the original image on the left and the recognition results in real time on the right. The operation is simple and intuitive, fully meeting clinical needs and providing strong technical support for TCM clinical practice.

[0114] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided by this invention can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), memory bus (RAMbus), direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0115] In summary, this invention provides a method for stably identifying acupoints on the human back. This method includes: acquiring a back image of the current user; obtaining the location coordinates of reference acupoints based on the back image; calculating the current user's body proportions based on the location coordinates of the reference acupoints; dividing the reference acupoints into several groups containing symmetrical reference acupoints; calculating representative points on the left and right sides of each group based on the location coordinates; determining a reference straight line based on the representative points; obtaining a spinal alignment marker line for the current user based on the reference straight line; and calculating the specific locations of other acupoints based on the body proportions and the spinal alignment marker line. This invention, by acquiring a back image of the current user, accurately marking the location coordinates of reference acupoints, dividing these reference acupoints into several groups, calculating representative points for each group, determining a reference straight line based on the representative points, and then generating a spinal alignment marker line, can accurately determine the specific locations of acupoints by combining the spinal alignment marker line with the body proportions. Compared with existing technologies, this invention achieves accurate acupoint marking by comprehensively considering spinal alignment and body proportions. This not only significantly increases the number of identifiable acupoints and improves identification efficiency, but also ensures the accuracy and physiological rationality of the positioning results.

[0116] It should be understood that the application of the present invention is not limited to the examples above. Those skilled in the art can make improvements or modifications based on the above description, and all such improvements and modifications should fall within the protection scope of the appended claims.

Claims

1. A method for reliably identifying acupoints on the human back, characterized in that, The method for stably identifying acupoints on the human back includes: Obtain the back image of the current user, obtain the positioning coordinates of the reference acupoints based on the back image, and calculate the body proportions of the current user based on the positioning coordinates of the reference acupoints. The reference acupoints are divided into several groups containing left and right symmetrical reference acupoints. Representative points on the left and right sides of each group are calculated based on the positioning coordinates. A reference straight line is determined based on the representative points. Obtain the spine alignment marker line for the current user based on the reference straight line; Calculate the specific locations of other acupoints based on the human body proportions and the spinal alignment marking lines; The step of calculating the representative points on the left and right sides of each group based on the positioning coordinates includes: Calculate the representative points in each of the aforementioned groups. and ; The representative point This represents the average value of several acupoints on the left side of the group. The representative point This represents the average value of several acupoints on the right side of the group. Determining the reference line based on the representative point includes: Based on the representative points in several of the aforementioned groups and Calculate the baseline of the corresponding group slope and intercept According to the slope and intercept Determine the reference straight line ; The slope The calculation formula is: ; The intercept The calculation formula is: ; The step of obtaining the current user's spine orientation marker line based on the reference straight line includes: Based on several of the aforementioned reference lines Calculate the slope of the spinal alignment marking line. According to the slope On the reference straight line The center point of the spine orientation marker line is generated; The slope of the spine alignment line The calculation formula is: ; The calculation of the specific locations of other acupoints based on the human body proportions and the spinal alignment marking lines includes: Calculate the basic scale According to the aforementioned basic scale Determine the specific location of other acupoints ; The basic scale The highest point in the group and lowest point The distance between; The basic scale The calculation formula is: ; The specific locations of the other acupoints The calculation formula is: ； ； t is a proportional coefficient determined according to the traditional theory of bone measurement.

2. The method for stably identifying acupoints on the human back according to claim 1, characterized in that, The step of obtaining the current user's back image and obtaining the location coordinates of the reference acupoints based on the back image includes: The trained model is used to process the current user's back image; Before processing the back image of the current user using the trained model, the following steps are also included: A training model is constructed, which includes a human back acupoint dataset, comprising several human back images with coordinate data of the reference acupoints.

3. The method for stably identifying acupoints on the human back according to claim 2, characterized in that, The human back acupoint dataset also includes augmented data; The enhanced data is an image obtained by randomly rotating, scaling, and brightness-processing several pairs of images of the human back.

4. The method for stably identifying acupoints on the human back according to claim 1, characterized in that, The method of dividing the reference acupoints into several groups including bilaterally symmetrical reference acupoints includes: Grouped according to the location of the reference acupoints in the back image; The groups include the shoulder area group, the mid-back area group, and the waist area group; The shoulder area group includes eight acupoints symmetrically located on both sides: Jianzhongyu, Jianwaiyu, Bingfeng, and Tianzong. The central back area group includes six acupoints symmetrically placed on both sides: Geshu, Hunmen, and Sanjiaoshu. The lumbar region group includes 12 acupoints symmetrically placed on both sides: Guanyuanshu, Pangguanshu, Baihuanshu, Zhibian, Huiyang, and Jingmen.

5. The method for stably identifying acupoints on the human back according to claim 4, characterized in that, The step of dividing the reference acupoints into several groups including bilaterally symmetrical reference acupoints further includes: Alternatively, grouping can be based on the meridian connections of the reference acupoints in the back images; Alternatively, grouping based on the functional attributes of the reference acupoints in the back image; Alternatively, grouping based on the recognition confidence of the reference acupoints in the back images.

6. A smart terminal, characterized in that, The smart terminal includes a memory, a processor, and a program for stably identifying acupoints on the back of the human body stored in the memory and executable on the processor. When the processor executes the program for stably identifying acupoints on the back of the human body, it implements the method for stably identifying acupoints on the back of the human body as described in any one of claims 1-5. The smart terminal also includes a display, which can simultaneously display at least two display pages. One display page is used to display the back image of the current user, and the other display page is used to display the back image of the current user after marking the reference acupoints and other acupoints.

Images