一种基于深度学习的二阶段舌象分割网络模型

A Two-Stage Tongue Demonstration Segmentation Network Model Based on In-DepthLearning

目的:为了改善传统的图像分割算法需要人为干预且分割精度低,探讨基于深度学习的二阶段舌象分割网络模型提高分割精度。方法:将基于深度学习的二阶段舌象分割网络模型分为粗分割和精分割两个部分,粗分割定位舌体去除无关干扰信息,精分割实现舌象的像素级精细分类分割。对分割后的舌象图片进行形态学优化,进一步优化分割结果。结果:本分割网络模型平均交并比为95.25%,比主流卷积神经网络模型高出3.10%。结论:基于深度学习的二阶段舌象分割网络模型优于传统图像分割算法和主流卷积神经网络模型,在不同类型的数据集上能准确分割舌体,有较高的精度和鲁棒性。

Objective:To improve the traditional tongue demonstration segmentation,which requires human intervention with low segmentation accuracy,and to explore a two-stage tongue demonstration segmentation network model based on in-depth learning,so as to improve the segmentation accuracy.Methods:It is mainly divided into rough segmentation and fine segmentation.Rough segmentation is to divide the tongue body to remove irrelevant interference information,and fine segmentation realizes pixel-level fine classification and segmentation of tongue demonstration.Morphological optimization was performed on the segmented tongue demonstration to further optimize the segmentation results.Results:The average intersection ratio of this segmentation network model reached 95.25%,which was 3.10%higher than the mainstream convolutional neural network model.Conclusion:The experimental results show that the network model proposed in this study is superior to traditional image segmentation algorithms and mainstream convolutional neural network models,and can accurately segment the tongue on different types of data sets,with high accuracy and robustness.