Sublingual Veins Extraction Method Based on Hyperspectral Tongue Images
Sublingual vein is one of the important features ontongue surface, which may have pathological relationship withsome diseases. Extracting sublingual veins accurately is theprimitive work of computer-aided tongue disease diagnosis. Mostexisting sublingual veins extraction methods are using sublingualimages captured by traditional CCD cameras. However, theseconversional methods impede the accurate analysis on thesubjects of sublingual veins because of the limited information of the images. To solve these issues, a hyperspectral tongue imagingsystem instead of a digital camera is used to capture sublingualimages. Then an improved spectral angle mapper (ISAM)algorithm for automatic sublingual veins extraction waspresented. In this algorithm, the spectral of sublingual veins wereextracted and the spectral angles of all bands and partial bandswere calculated respectively. Finally, the sublingual veins wereextracted according to the spectral angles. The experimentalresults demonstrate that this algorithm can extract the sublingualveins more accurately.
Qingli Li Yiting Wang Hongying Liu Zhen Sun
Key Laboratory of Polor Materials and Devices East China Normal University Shanghai 200241, China Department of Traditional Chinese Medicine Second Military Medical University Shanghai, China
国际会议
成都
英文
1-3
2010-06-18（万方平台首次上网日期，不代表论文的发表时间）