Traditional Chinese Medicine practitioners usually observe the color and coating of a patient's tongue to determine ZHENG (such as Cold or Hot ZHENG) and to diagnose different stomach disorders including gastritis. In our previous work, we explored new modalities for clinical characterization of ZHENG in gastritis patients via tongue image analysis using various supervised machine-learning algorithms. We proposed a system that learns from the clinical practitioner's subjective data how to classify a patients health status by extracting meaningful features from tongue images based on color-space models. In this paper, we propose an enhancement to the ZHENG classification system: a coating separation technique using the MSF images such that feature extraction is applied only to the coated region on the tongue surface. The results obtained over a set of 263 gastritis patients (most of whom are either Cold Zheng or Hot ZHENG), and a control group of 48 healthy volunteers demonstrate an improved performance for most of the classification types considered. © 2012 IEEE.


Electrical and Computer Engineering

Keywords and Phrases

Chromaticity; color space features; machine learning; Reflection components separation; Specular reflection; ZHENG classification

International Standard Book Number (ISBN)


Document Type

Article - Conference proceedings

Document Version


File Type





© 2023 Institute of Electrical and Electronics Engineers, All rights reserved.

Publication Date

01 Dec 2012