摘要
舌诊是中医四诊的重要内容,为中医临床必察之项。古往今来,为名医者莫不精深于舌诊。颜色特征是诊断的重要特征,对其进行识别(分类)的好坏将直接影响舌诊诊断系统的准确性。利用主成分分析(PCA)的全局性,在HSV颜色空间中对舌象进行特征提取、降维,并通过A daBoost把一系列弱分类器提升为强分类器,对舌象颜色进行了深入的分类研究。结果表明,此算法是有效的。
Tongue diagnosis is an important part of the four diagnoses in Traditional Chinese Medicine （TCM）. It is a necessary component in clinical diagnosis. Those famous doctors,who lived in ancient or modern society,are good at tongue diagnosis. The color of tongue is important in a system of automatic diagnosis in TCM and the quality of the color classification directly affects the performance of tongue diagnosis. The method of the color classification of tongue was proposed ,which adopted the principal com- ponent analysis to reduce the number of dimensions without much loss of information and AdaBoost to converge on the global minimum in HSV space. Experiments on real tongue image show the method is effective.
出处
《广西师范大学学报（自然科学版）》
CAS
北大核心
2009年第3期158-161,共4页
Journal of Guangxi Normal University:Natural Science Edition
基金
国家自然科学基金资助项目(60702069)
浙江省自然科学基金资助项目(Y1080851)
关键词
舌诊
HSV
主成分分析AdaBoost
中医
tongue diagnosis HSV principal component analysis AdaBoost Traditional Chinese Medicine
