基于最大类间方差法和区域生长的舌体自动分割

An automatic tongue segmentation algorithm based on OTSU and region growing

舌图像中舌体的分割是舌诊信息化和客观化的基础。文章根据舌图像的特点,提出了基于最大类间方差法和子块生长的舌体自动分割算法,通过均值偏移对图像进行预处理,再利用最大类间方差法对彩色舌图像进行自动分类,最后基于分类后的子块特征进行区域生长,实现舌图像中舌体区域的自动分割。实验对DS01-A舌面脉信息采集体质辨识系统采集的100张舌图像进行分割,能够准确地分割出舌体区域。

The segmentation of tongues in tongue images is the basis of informatization and objectification tongue diagnosis. Based on the characteristics of the tongue image, an automatic segmentation algorithm based on OTSU method and sub - block re- gion growing is proposed. The image is preprocessed by mean shift, and the color tongue image is automatically classified by OT- SU method. Finally, the sub - block region growing method is used based on the merging criterion, which is automatically calcu- lated based on the feature of the sub - block. And the final merged region is the tongue area. Experiments show that the proposed algorithm can accurately segment the tongue area from 100 tongue images, which are collected by DS01 -A tongue veins informa- tion collection system.