Skew tongue detection method and device, electronic equipment and medium

Abstract

The invention provides a skew tongue detection method and device, electronic equipment and a medium, and the method comprises the steps: obtaining a to-be-detected image of a target object, carrying out the head posture detection of a head region in the to-be-detected image, and obtaining the head posture information corresponding to the head region; the tongue body area in the detection image is detected, and tongue body information corresponding to the tongue body area is obtained; calculating the head posture information and the tongue body information by adopting a preset inclination degree algorithm to obtain a tongue body inclination degree value of the target object; and if the tongue body inclination degree value is greater than a preset inclination threshold value, determining that the tongue body of the target object is an inclined tongue. According to the method, the detection accuracy is improved.

Description

technical field [0001] The present application relates to the technical field of image processing, in particular, to a method, device, electronic equipment and medium for detecting a skewed tongue. Background technique [0002] The tongue is naturally protruded, and the tongue body is deviated to one side, left or right and cannot be straightened, which is called a crooked tongue. The tongue muscle on the affected side is paralyzed and unable to contract. When it is stretched a little, the tongue body will be uneven and skewed on both sides. Therefore, when the left tongue muscle is paralyzed, the tip of the tongue will turn to the left, and when the right tongue muscle is paralyzed, the tongue tip will deviate to the right. This disease is common in stroke, that is, cerebrovascular accident. If it is a local disease, it is caused by compression of the hypoglossal nerve or facial nerve paralysis. [0003] Computer vision analyzes the skew of the tongue and analyzes the ske...

AI Technical Summary

Problems solved by technology

[0003] Computer vision analyzes the skew of the tongue and analyzes the skewed tongue, usually through techniques such as skeleton extraction and refinement, method of moments, mid-axis transformation, and straight line fitting. However, these technologies have their own shortcomings, such as skeleton extraction and refinement, and mid-axis transformation. It is only applicable to slender tongues, and the method of moments is only applicable to tongues with better contour symmetry.

[0004] That said, there are certain limitations to the analytical techniques described above.

Images