齿痕舌像自动分割的方法

Method of Automatic Tongue Area Extraction in Tooth-Marked Tongue Images

通过总结前人分割舌像的经验,在对齿痕一类舌像特征分析后,确定将RGB模型的舌图先转换为HSV模型,然后运用Otsu阈值法和分量互补的方法分割出完整的齿痕舌体图像。这种方法保留了齿痕的特点使识别齿痕成为可能。齿痕舌分割方法是齿痕舌数字化的基础,它进一步奠定了中医舌诊数字化的基础。

Summarizes the experience of body of tongue segmentation of the predecessors. After analyzing the characteristic of the kind of tooth- marked tongue, it was made sure that conversion from RGB model to HIS model,and then using Otsu threshold value and H,S, V component supplementary method complete segmentation of tooth - marked tongue image. This method retains mast of the important characteristics of the tooth- marked, which makes recognition tooth - marked possible. It will help improve the digitization of the tradi- tional Chinese medicine （TCM） tongue diagnosis foundation.