Tongue crack feature extraction method based on wavelet transformation

Abstract

The invention discloses a tongue crack feature extraction method based on wavelet transformation, which comprises the following steps of: acting median filtering on an original tongue image to smoothnoise interference factors in the original tongue image; segmenting the smoothed tongue image by using a Canny edge detection operator; performing wavelet decomposition on the segmented tongue image to obtain a high-frequency tongue image component graph and a low-frequency tongue image component graph; fusing the high-frequency component graph and the low-frequency component graph by using a wavelet fusion technology; and reconstructing clear tongue crack characteristics through wavelet inverse transformation. The wavelet function is decomposed and reconstructed, and the wavelet function is applied to tongue crack image processing, including tongue image denoising; And by adding a wavelet transformation processing technology, the feature extraction and matching of the tongue crack image can be more accurate.

Description

technical field [0001] The invention belongs to the technical field of traditional Chinese medicine, and in particular relates to a tongue crack feature extraction method based on wavelet transform. Background technique [0002] Traditional Chinese medicine believes that changes in the tongue can reflect the diseased state of the patient's internal organs. Through the examination of the patient's tongue, the doctor can find out the abnormal function of a certain part of the patient in time, which plays a good auxiliary role in the diagnosis of some diseases. In traditional Chinese medicine, the doctor examines the patient through the "four diagnosis" to judge the physiological and pathological status of the patient's qi and blood, yin and yang in the viscera. The "four diagnosis" in TCM diagnosis are divided into four ways: looking, smelling, asking, and feeling. Among them, tongue diagnosis is an important part of TCM diagnosis and plays an important role in clinical diseas...

AI Technical Summary

Problems solved by technology

Although the method based on line detection considers the texture features of the tongue crack, there are some shortcomings. to the closed contour; the line detection method based on the center line generally uses the second order derivative, which is also sensitive to noise, and there is often a large error in the extraction of the center line position; while the line detection method based on the area often makes the tongue coating Coarse textures and pseudo cracks on the surface are also segmented, and redundant textures need to be manually removed to segment cracks

Images