Crack tongue detection system based on artificial intelligence

Abstract

The invention relates to the technical field of artificial intelligence, in particular to a crack tongue detection system based on artificial intelligence. The system comprises: an image acquisition module used for acquiring a tongue image of a to-be-tested person; the semantic segmentation module that is used for obtaining a target area of the tongue, obtaining a semantic segmentation graph on the tongue through a semantic segmentation network and carrying out connected domain analysis to obtain the direction, the number and the area of each crack; the extension invariance module that is usedfor calculating the depth of the crack and obtaining extension invariance characteristics according to the depth of the crack and the area of the crack; and the crack state judgment module that is used for obtaining the state of the cracks according to the extension invariance characteristics of the cracks, the number of the cracks and the directions of the cracks to reflect the health conditionof the body. According to the invention, the extension invariance characteristic of the crack can be constructed by using the characteristic relation in the depth and the area of the tongue crack, sothat the severity of the tongue crack can be reflected more accurately.

Description

technical field [0001] The invention relates to the technical field of artificial intelligence, in particular to an artificial intelligence-based cracked tongue detection system. Background technique [0002] The tongue is an important organ of the human body. Traditional Chinese medicine believes that the tongue is connected to the five internal organs through the meridians. Therefore, the deficiency and excess of the human viscera, qi, blood, and body fluids, as well as the severity of diseases, can all be objectively reflected in the tongue image. The tongue can reflect the physical health status. Cracked tongue is a common symptom. It is mainly manifested as a relatively large tongue body with numerous criss-cross grooves of different depths on the surface. [0003] The shallow cracks on the tongue are mainly caused by the atrophy of the tongue mucosa, which makes the longitudinal or horizontal stripes of the tongue protrude from the surface, while the deep cracks on th...

AI Technical Summary

Problems solved by technology

Therefore, it is necessary to detect the direction, depth, and size distribution of cracked tongue cracks in tongue diagnosis for the diagnosis of physical health. The existing cracked tongue detection mostly uses neural networks to detect the shape of cracks, and then detects the cracks through the depth and size of cracks. During quantitative analysis, the detection of crack severity will be affected due to irregular changes in shape

Images