北京航空航天大学学报 ›› 2019, Vol. 45 ›› Issue (12): 2364-2374.doi: 10.13700/j.bh.1001-5965.2019.0370

• 论文 • 上一篇    下一篇

基于DCNN和全连接CRF的舌图像分割算法

张新峰, 郭宇桐, 蔡轶珩, 孙萌   

  1. 北京工业大学 信息学部, 北京 100124
  • 收稿日期:2019-07-09 出版日期:2019-12-20 发布日期:2019-12-31
  • 通讯作者: 张新峰 E-mail:zxf@bjut.edu.cn
  • 作者简介:张新峰 男,博士,副教授,硕士生导师。主要研究方向:图像处理、模式识别、机器学习;郭宇桐 男,硕士研究生。主要研究方向:图像处理、深度学习、语义分割。
  • 基金资助:
    国家重点研发计划(2017YFC1703300)

Tongue image segmentation algorithm based on deep convolutional neural network and fully conditional random fields

ZHANG Xinfeng, GUO Yutong, CAI Yiheng, SUN Meng   

  1. Faculty of Information Technology, Beijing University of Technology, Beijing 100124, China
  • Received:2019-07-09 Online:2019-12-20 Published:2019-12-31
  • Supported by:
    National Key R&D Program of China (2017YFC1703300)

摘要: 针对中医舌诊中舌体分割不准确、分割速度较慢且需要人工标定候选区域等问题,提出了一种端到端的舌图像分割算法。与传统舌图像分割算法相比,所提算法可以得到更为准确的分割结果,并且不需要人工操作。首先,使用孔卷积算法,可以在不增加参数的条件下扩大网络的特征图谱。其次,使用孔卷积空间金字塔池化(ASPP)模块,令网络通过不同的感受野学习舌图像的多尺度特征。最后,将深度卷积神经网络(DCNN)和全连接的条件随机场(CRF)相结合,细化分割后的舌体边缘。实验结果表明:所提算法优于传统舌图像分割算法和主流的深度卷积神经网络,具有较高的分割精度,平均交并比达到了95.41%。

关键词: 深度学习, 卷积神经网络(CNN), 语义分割, 舌图像, 条件随机场(CRF)

Abstract: The disadvantage of tongue image segmentation in traditional Chinese medicine are low accuracy, slow segmentation speed and manual calibration of candidate regions.To solve these problems, we propose an end-to-end tongue image segmentation algorithm. Compared with the traditional tongue segmentation algorithm, more accurate segmentation results can be obtained by the proposed method which does not need any manual operation. Firstly, the atrous convolution algorithm is used to increase the feature map of the network without increasing the parameters. Secondly, the atrous spatial pyramid pooling (ASPP) module is used to enable the network to learn the multi-scale feature of the tongue image through different receptive fields. Finally, the deep convolutional neural networks (DCNN) are combined with fully connected conditional random fields (CRF) to refine the edge of the segmented tongue image. The experimental results show that the proposed method outperforms traditional tongue image segmentation algorithm and popular DCNN with higher segmentation accuracy, and the mean intersection over union reaches 95.41%.

Key words: deep learning, convolutional neural network (CNN), semantic segmentation, tongue images, conditional random fields (CRF)

中图分类号: 


版权所有 © 《北京航空航天大学学报》编辑部
通讯地址:北京市海淀区学院路37号 北京航空航天大学学报编辑部 邮编:100191 E-mail:jbuaa@buaa.edu.cn
本系统由北京玛格泰克科技发展有限公司设计开发