期刊论文

A Tongue Segmentation Method Based on Instance Segmentation

中文

中国卫生信息管理杂志

1672-5166

2023

20

03

459-464

10.3969/j.issn.1672-5166.2023.03.022

本校为第一机构

目的 使用实例分割算法提高舌体分割的准确性，并支持智能舌诊。方法 将采集到的962张分辨率为5568×3712的舌面图像，预裁剪为1400×1400，图像中保留舌体、唇部和少部分皮肤；然后采用数据标注工具Labelme对舌体进行标注，并使用BlendMask算法分割舌体。结果 BlendMask算法的定位精度为99.77%，而分水岭算法、GrabCut算法和Mask R-CNN算法的定位精度分别为45.20%、70.52%和93.37%。BlendMask算法的定位精度与上述3种算法相比分别提高了54.57%、29.25%和6.40%。结论 BlendMask算法可以准确分割舌体，支持智能舌诊，为中医智能化舌诊提供参考。

Objective To improve the accuracy in segmenting tongues and support intelligent tongue diagnosis by using instance segmentation algorithm.Methods The collected 962 tongue images with a resolution of 5568×3712 were pre-cropped to 1400×1400.The tongues,lips and ...MORE Objective To improve the accuracy in segmenting tongues and support intelligent tongue diagnosis by using instance segmentation algorithm.Methods The collected 962 tongue images with a resolution of 5568×3712 were pre-cropped to 1400×1400.The tongues,lips and a small part of th...