Computational tongue color simulation in tongue diagnosis

Hung Shing Chen, Shih Ming Chen, Chen Yu Jiang, Yi Chen Zhang, Chia Yu Lin, Chia En Lin, Jen Ai Lee

Research output: Contribution to journalArticlepeer-review

Abstract

Tongue color is one of the important indices for tongue diagnosis in traditional Chinese medicine. This study aims to analyze tongue colors of computational tongue diagnosis in traditional Chinese medicine using scientific quantification and computational simulation. The tongue color data are established according to the experiment in which the doctors who use Chinese traditional medicine assessed standard Munsell color charts under the standard lighting environment. Tongue color is classified into six color names, which are pale red, light red, red, crimson, dark red, and purple. The doctors assessed Munsell color charts to find the corresponding color charts' distributions of each color name in tongue color. The hue-lightness-chroma data of the chosen Munsell color charts were transformed to CIE xyY using the look-up table computation, then further were converted to CIELAB values and sRGB data. Based on the 95% confidence ellipses formed on CIELAB (a*, b*) plane and CIELAB (C*, L*) plane, the comparisons between tongue colors and general colors were analyzed. The computational tongue image simulation combining the elements of color, texture, and moisture was successfully established. This computational simulation method could potentially become a useful tool for teaching and learning diagnoses in the education of Chinese medicine.

Original languageEnglish
JournalColor Research and Application
DOIs
Publication statusAccepted/In press - 2021

Keywords

  • computational tongue appearance simulation
  • computational tongue diagnosis
  • tongue color

ASJC Scopus subject areas

  • Human Factors and Ergonomics
  • Chemistry(all)
  • Chemical Engineering(all)

Fingerprint

Dive into the research topics of 'Computational tongue color simulation in tongue diagnosis'. Together they form a unique fingerprint.

Cite this