DocumentCode :
3458643
Title :
Gloss Feature Extraction for Surface Examination in Traditional Chinese Medicine
Author :
Zhou, Rui ; Zhao, Rui-Wei ; Li, Fu-Feng ; Li, Guo-Zheng ; Zheng, Xiao-Yan
Author_Institution :
Diagnosis Lab. of Traditional Chinese Med., Shanghai Univ. of Traditional Chinese Med., Shanghai, China
fYear :
2010
fDate :
21-23 Oct. 2010
Firstpage :
1
Lastpage :
5
Abstract :
In TCM theory, brightness and moisture is recognized as the Qi , blue red yellow white and black is recognized as the color, the five colors charges blood, the gloss charges Shen. We may diagnose the internal organs´ essence by observing the changes of face gloss, which is a very important way to judge the condition and extrapolate the prognosis. However, because of lacking of objective data, the traditional way of observing face gloss mainly depends on clinicians´ subjective appraises, which becomes one of the most important factors that hampers TCM´s development. As a grope and study for the objective TCM, we utilize the computer vision skills and apply the feature extraction methods, like PCA, 2DPCA and (2D)2PCA, to the face samples under4 color spaces as facial gloss extraction methods. The result indicats that three methods have a positive effect on extracting gloss information from faces, (2D)2PCA may reach to the rate of 84.5% in the HSV color space. This article has try to explore TCM intellectualization and TCM Informationization, and attain positive experimental results. It provides one new method for the TCM observation of gloss quantification examination.
Keywords :
blood; computer vision; feature extraction; image colour analysis; medical image processing; medicine; skin; Chinese medicine; HSV color space; PCA; TCM informationization; TCM theory; color space; computer vision; face sample; feature extraction method; gloss feature extraction; gloss information; prognosis; surface examination; Electronic mail; Face; Face recognition; Feature extraction; Image color analysis; Medical diagnostic imaging; Principal component analysis;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Pattern Recognition (CCPR), 2010 Chinese Conference on
Conference_Location :
Chongqing
Print_ISBN :
978-1-4244-7209-3
Electronic_ISBN :
978-1-4244-7210-9
Type :
conf
DOI :
10.1109/CCPR.2010.5659278
Filename :
5659278
Link To Document :
بازگشت