A tongue image segmentation method, device and storage medium

Abstract

The present invention relates to a tongue image segmentation method, device and storage medium, wherein the method includes: marking the background area and the tongue body area for each tongue image image, and the pixel values ​​are recorded as 0 and 1 respectively; The image set is used to train the binary classification semantic segmentation network model; the target image is input into the binary classification semantic segmentation network model to obtain the first binarized prediction image of the same size, the pixel value of the background area is 0, and the pixel value of the tongue body area is 1 ;Detect the connected regions in the image, keep the one with the largest area, and adjust the pixel values ​​of other connected regions from 1 to 0; scan by row, calculate the coordinates of the first pixel value of each row from left to right and the last one The coordinates with a pixel value of 1, scan the pixel value between these two coordinates, when a coordinate a that is not 1 is found, adjust the pixel value corresponding to a to 1; the color value corresponding to the coordinate with a pixel value of 0 Adjust to a uniform color to generate the target tongue segmentation image.

Description

technical field [0001] The present invention relates to the field of medical diagnosis and treatment, and more specifically, relates to an artificial intelligence-based tongue image segmentation method, device and storage medium. Background technique [0002] Tongue image refers to the representation of the human tongue. Chinese medicine pays attention to seeing, hearing, asking and feeling. The tongue image is one of the signs of physical condition. By observing the state of the tongue image, such as the color and thickness of the tongue coating, TCM doctors can judge certain diseases of the patient, such as whether there is stomach disease, diabetes, etc. [0003] However, the judgment of TCM doctors is based on their rich experience and depends on their personal inspection, which is not conducive to the self-examination and self-diagnosis of patients; at the same time, due to the limitations of knowledge and experience, it is impossible for patients to make relatively acc...

AI Technical Summary

Problems solved by technology

[0003] However, the judgment of TCM doctors is based on their rich experience and depends on their personal inspection, which is not conducive to the self-examination and self-diagnosis of patients; at the same time, due to the limitations of knowledge and experience, patients have no way to make relatively accurate The initial judgment, but the current shortage of medical resources and the fatigue of going to and from the hospital make it impossible for patients to understand the condition in a timely and effective manner

Images