Facial image medical analysis system using quantitative chromatic feature

Xingzheng Wang, Bob Zhang, Zhenhua Guo, Dapeng Zhang

Research output: Journal article publicationJournal articleAcademic researchpeer-review

20 Citations (Scopus)


In order to investigate whether the appearance of a human face can be utilized for diagnostic purposes, which have been practiced for thousands of years in Traditional Chinese Medicine (TCM), this paper aims to present a computerized facial image analysis system by using quantitative chromatic features for disease diagnosis applications. A face image acquisition device is dedicatedly designed to acquire image samples from volunteers who have three types of health conditions: normal health, icterohepatitis, and severe hepatitis. Then, after color calibration on the acquired images to remove noises caused by lighting fluctuations, quantitative dominant color features are extracted by fuzzy clustering method. In order to further improve the diagnosis accuracy, a feature selection procedure is involved to identify the most discriminative feature subset for the diagnostic classification. Lastly, based on these selected quantitative feature, each face image could be diagnosed into different health groups. Experiments are conducted based on a database which includes over 300 sample images, and the result shows that the overall diagnosis accuracy between healthy samples and other two diseases is higher than 88%. Hence the feasibility of disease diagnosis by inspecting the chromatic feature of human face could be verified.
Original languageEnglish
Pages (from-to)3738-3746
Number of pages9
JournalExpert Systems with Applications
Issue number9
Publication statusPublished - 1 Jul 2013


  • Chromatic feature
  • Dominant color
  • Face diagnosis
  • Medical face image analysis
  • Traditional Chinese Medicine

ASJC Scopus subject areas

  • General Engineering
  • Computer Science Applications
  • Artificial Intelligence


Dive into the research topics of 'Facial image medical analysis system using quantitative chromatic feature'. Together they form a unique fingerprint.

Cite this