CN-116128814-B - Standardized acquisition method and related device for tongue diagnosis image

CN116128814BCN 116128814 BCN116128814 BCN 116128814BCN-116128814-B

Abstract

The application relates to a standardized acquisition method and a related device of tongue diagnosis images, wherein the method comprises the following steps of obtaining continuous multi-frame tongue diagnosis acquisition images; the tongue diagnosis image determining method comprises the steps of responding to an acquired tongue diagnosis acquisition image, analyzing the tongue diagnosis acquisition image to determine that the tongue diagnosis acquisition image comprises a mouth and a tongue, extracting and analyzing the tongue diagnosis acquisition image to extract a plurality of mouth characteristic areas and tongue characteristic areas, analyzing each mouth characteristic area and each tongue characteristic area to obtain a corresponding tongue characteristic model, obtaining a plurality of model parameters based on the tongue characteristic model, obtaining a matching value based on model parameter operation, and determining a tongue diagnosis image determining result based on the matching value. The application has the advantages of providing standard tongue diagnosis images for patients quickly and improving tongue diagnosis efficiency.

Inventors

SHI JINGMING
WU XINYONG
LIU BIN

Assignees

上海融达信息科技有限公司

Dates

Publication Date: 20260508
Application Date: 20221220

Claims (6)

1. The standardized acquisition method of the tongue diagnosis image is characterized by comprising the following steps of: acquiring continuous multi-frame tongue diagnosis acquisition images; Responding to the acquired tongue diagnosis acquisition image, analyzing the tongue diagnosis acquisition image, and determining that the image comprises a mouth and a tongue; extracting and analyzing the tongue diagnosis acquisition image, and extracting a plurality of mouth characteristic areas and tongue characteristic areas; Analyzing each mouth characteristic region and each tongue characteristic region to obtain a corresponding tongue characteristic model; obtaining a plurality of model parameters based on the tongue characteristic model, obtaining a matching value based on model parameter operation, and determining a tongue diagnosis image determination result based on the matching value; the step of extracting and analyzing the tongue diagnosis acquisition image to extract a plurality of mouth characteristic areas and tongue characteristic areas comprises the following steps: Acquiring a plurality of preset mouth recognition models and tongue recognition models; obtaining a mouth characteristic region based on a preset mouth recognition model, and obtaining a tongue characteristic region based on a preset tongue recognition model, wherein the mouth characteristic region distinguishes an upper lip and a lower lip; the step of analyzing each mouth feature area and each tongue feature area to obtain a corresponding tongue feature model includes: Obtaining a longitudinal center axis based on the relative positions of the upper lip and the lower lip, wherein the upper lip and the lower lip are symmetrical based on the longitudinal center axis; demarcating the tongue image into a left tongue image and a right tongue image based on a longitudinal medial axis; Respectively extracting edges of the left tongue image and the right tongue image to obtain a tongue edge contour feature model; The step of obtaining a plurality of model parameters based on the tongue characteristic model, obtaining a matching value based on model parameter operation, and determining a tongue diagnosis image determination result based on the matching value comprises the following steps: and carrying out tongue image edge smoothing processing, calculating the curvature degree of the left tongue image edge and the right tongue image edge to judge the tongue shape, and taking the curvature extremum of the tongue image edge as the tongue tip, wherein the tongue shape comprises a conventional tongue shape and a tongue separating tongue shape.
2. The standardized acquisition method of a tongue diagnosis image according to claim 1, wherein the step of obtaining a plurality of model parameters based on the tongue feature model, obtaining a matching value based on the model parameter operation, and determining a tongue diagnosis image determination result based on the matching value further comprises: calculating the symmetry degree of the left tongue image edge and the right tongue image edge to obtain a first matching value; and calculating the length-width ratio of the left tongue image edge to the right tongue image edge to obtain a second matching value.
3. The method for standardized acquisition of tongue diagnostic images according to claim 2, wherein the step of calculating the degree of symmetry of the left tongue image edge and the right tongue image edge to obtain the first matching value comprises: Collecting a plurality of calculation points along the longitudinal center axis, and respectively making vertical lines of the longitudinal center axis from the calculation points to the two sides until the left tongue image edge and the right tongue image edge; Calculating the length ratio of the vertical lines at two sides of the same calculation point, judging whether the ratio result falls within a preset threshold value interval, if so, taking the ratio result as a qualified point, otherwise, taking the ratio result as an unqualified point; the ratio of the number of fit points to the number of non-fit points is calculated as a first matching value.
4. The method for standardized acquisition of tongue diagnostic images of claim 3 wherein the step of calculating the aspect ratio of the left tongue image edge to the right tongue image edge to obtain the second matching value comprises: generating a reference axis parallel to the longitudinal central axis based on the position of the tongue tip; Collecting a plurality of reference points along a reference axis, and respectively making vertical lines from the reference points to two sides until adjacent tongue image edges and longitudinal center axes; And calculating the ratio of the sum of the vertical lines on two sides of the same reference point to the distance from the reference point to the corresponding tongue tip of the reference axis, and taking the ratio as a second matching value.
5. An electronic device, comprising: One or more processors; A memory; One or more applications, wherein the one or more applications are stored in the memory and configured to be executed by the one or more processors, the one or more application applications configured to: a standardized acquisition method of a tongue diagnostic image according to any one of claims 1 to 4 is performed.
6. A computer readable storage medium storing at least one instruction, at least one program, code set, or instruction set, the at least one instruction, the at least one program, the code set, or instruction set being loaded and executed by a processor to implement: a method of standardized acquisition of lingual images according to any one of claims 1 to 4.

Description

Standardized acquisition method and related device for tongue diagnosis image Technical Field The application relates to the field of image detection, in particular to a standardized acquisition method and a related device for tongue diagnosis images. Background With the advent of the medical automation age, online pharmacy and hospitals gradually open the functions of automatic consultation, automatic prescription and the like. For example, by carrying out image acquisition and feature recognition on the facial facies of a person, the associated symptoms possibly related to the patient can be primarily judged. The features of the face are mainly concentrated in the five sense organs, are located on the skin, are uniformly distributed on the whole, and have small adjacent feature interference, so that the image acquisition of the face is mature at present. However, for tongue diagnosis, the tongue features include tongue shape, tongue length, tongue width, tongue thickness, color, surface roughness, tongue coating distribution, tongue coating shape, tongue coating color, etc., and various features are concentrated on small tongue heads, so that standardized acquisition of tongue images is particularly important. In the actual operation process, some patients find that the tongue is involuntarily rolled, the tongue is too short to spit out, the left and right sides are inclined or the surface of the tongue is not facing the lens, so that the posture adjustment is required to be continuously carried out so as to achieve the standard posture. However, the tongue is relatively small and various characteristics are concentrated, so that a patient can hardly keep the tongue in the same form and shoot the tongue during image acquisition, and if the image acquired by the tongue is not standard, the tongue is difficult to match with standard templates in a database at a later stage for characteristic identification. Disclosure of Invention In order to facilitate patients to quickly provide standard tongue diagnosis images and improve tongue diagnosis efficiency, the application provides a standardized acquisition method and a related device of tongue diagnosis images. In a first aspect, the present application provides a standardized acquisition method for tongue diagnosis images, which adopts the following technical scheme: A standardized acquisition method of tongue diagnosis images comprises the following steps: image acquisition is carried out in real time to obtain continuous multi-frame tongue diagnosis acquisition images; Responding to the acquired tongue diagnosis acquisition image, analyzing the tongue diagnosis acquisition image, and determining that the image comprises a mouth and a tongue; extracting and analyzing the tongue diagnosis acquisition image, and extracting a plurality of mouth characteristic areas and tongue characteristic areas; Analyzing each mouth characteristic region and each tongue characteristic region to obtain a corresponding tongue characteristic model; and obtaining a plurality of model parameters based on the tongue characteristic model, obtaining a matching value based on model parameter operation, and determining a tongue diagnosis image determination result based on the matching value. By adopting the technical scheme, real-time image acquisition is carried out, and continuous multi-frame pictures are obtained, so that when a patient adjusts for many times according to requirements, tongue diagnosis images meeting requirements can be obtained in the tongue change process. And analyzing the tongue diagnosis image to obtain a mouth and a tongue in the tongue diagnosis acquisition image. The mouth is used for establishing a standard coordinate system to provide a reference for the position of the tongue, so that a tongue characteristic model based on the mouth reference is obtained. Compared with the scheme that the tongue is based on the self-established reference, the scheme can be compatible with the differences generated by different tongue shapes, and meanwhile the standardization degree is improved. Based on a plurality of model parameters obtained in the tongue characteristic model, different indexes can be respectively matched, and each matching value is synthesized to calculate whether the tongue diagnosis acquisition image meets the standard. In summary, by the standardized acquisition method of the tongue diagnosis image, standardized input of the tongue diagnosis image can be conveniently and rapidly carried out, standard tongue diagnosis images can be conveniently and rapidly provided by patients, and tongue diagnosis efficiency is improved. Optionally, the step of extracting and analyzing the tongue diagnosis acquisition image to extract a plurality of mouth feature areas and tongue feature areas includes: Acquiring a plurality of preset mouth recognition models and tongue recognition models; and obtaining a mouth characteristic region and a tongue characteristic reg