A Color Correction Method of TCM Tongue Image Based on k-pls Regression Model

Abstract

The invention discloses a color correction method of traditional Chinese medicine tongue images based on K-PLS regression model, which belongs to the interdisciplinary field of computer image processing and traditional Chinese medicine. The present invention designs a traditional Chinese medicine tongue image color correction method based on the kernel partial least squares regression model, which corrects the tongue images under different lighting environments to a unified standard to overcome the tongue image color presentation caused by the lighting difference of the tongue imager. The inconsistency problem makes the digital TCM tongue analysis results more objective and accurate. This invention uses a tongue imager to photograph and collect standard color code cards, then selects color code samples of the color code in the image, and uses the standard chromaticity value of each color in the color code as the target value to perform K-PLS regression model training , obtain a training model between the actual collected value of the color code and the standard value of the color code, use this training model to perform color regression correction on the actual tongue image taken in the shooting environment, and finally obtain the color-corrected TCM tongue image.

Description

technical field [0001] The invention belongs to the interdisciplinary field of computer image processing and traditional Chinese medicine, and designs a color correction method for tongue images in traditional Chinese medicine based on a K-PLS (Kernel Partial Least Squares) regression model. The image is calibrated to a unified standard to overcome the inconsistency of the color of the tongue image caused by the difference in illumination of the tongue imager, making the analysis results of the digital TCM tongue image more objective and accurate. Background technique [0002] Tongue diagnosis is an important content of inspection in traditional Chinese medicine "look, smell, ask, feel, four diagnosis combined with reference". For a long time, tongue diagnosis has mainly judged diseases and syndromes through the doctor's naked eye observation and experience, lacking quantitative measurement and analysis methods. In recent decades, research on the objectification of TCM, esp...

AI Technical Summary

Problems solved by technology

The reason is that changes in the lighting environment and different acquisition devices will inevitably cause color distortion in the acquired tongue images, as shown in the attached figure 1 As shown, the distortion of the color will not only make doctors make wrong judgments when observing the tongue, but also seriously affect the accuracy and objectivity of automatic analysis of tongue color and fur color.

However, due to the aging of the light source of the acquisition equipment and other reasons, color distortion is very easy to occur

Images