基于DCNN和全连接CRF的舌图像分割算法

doi:10.13700/j.bh.1001-5965.2019.0370

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

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

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

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/Abstract

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:

TN911.73

张新峰, 郭宇桐, 蔡轶珩, 孙萌. 基于DCNN和全连接CRF的舌图像分割算法[J]. 北京航空航天大学学报, 2019, 45(12): 2364-2374.

ZHANG Xinfeng, GUO Yutong, CAI Yiheng, SUN Meng. Tongue image segmentation algorithm based on deep convolutional neural network and fully conditional random fields[J]. JOURNAL OF BEIJING UNIVERSITY OF AERONAUTICS AND A, 2019, 45(12): 2364-2374.

参考文献

[1] SHEN L S,WANG A M,WEI B G,et al.Image analysis for tongue characterization[J].Acta Electronica Sinica,2001,12(3):317-323.
[2] 张灵,秦鉴.基于灰度投影和阈值自动选取的舌像分割方法[J].中国组织工程研究与临床康复,2010,14(9):1638-1641.ZHANG L,QIN J.Tongue-image segmentation based on gray projection and threshold-adaptive method[J].Journal of Clinical Rehabilitative Tissue Engineering Research,2010,14(9):1638-1641(in Chinese).
[3] 李丹霞,韦玉科.基于自适应阈值的舌像分割方法[J].计算机技术与发展,2011,21(9):63-65.LI D X,WEI Y K.Tongue image segmentation method based on adaptive thresholds[J].Computer Technology & Development,2011,21(9):63-65(in Chinese).
[4] KASS M,WITKIN A,TERZOPOULOS D.Snakes:Active,contour models[J].International Journal of Computer Vision,1988,1(4):321-331.
[5] 傅之成,李晓强,李福凤.基于径向边缘检测和Snake模型的舌像分割[J].中国图象图形学报,2019,14(4):688-693.FU Z C,LI X Q,LI F F.Tongue image segmentation based on snake model and radial edge detection[J].Journal of Image & Graphics,2009,14(4):688-693(in Chinese).
[6] LI Q L,XUE Y Q,WANG J Y,et al.Automated tongue segmentation algorithm based on hyperspectral image[J].Journal of Infrared & Millimeter Waves,2007,26(1):77-80.
[7] ROTHER C,KOLMOGOROV V,BLAKE A.GrabCut:Interactive foreground extraction using iterated graph cuts[J].ACM Transactions on Graphics,2004,23(3):309-314.
[8] 韦玉科,范鹏,曾贵.改进的GrabCut方法在舌诊系统中的应用[J].传感器与微系统,2014,33(10):157-160.WEI Y K,FAN P,ZENG G.Application of improved GrabCut method in tongue diagnosis system[J].Transducer & Microsystem Technologies,2014,33(10):157-160(in Chinese).
[9] 陈善超,符红光,王颖.改进的一种图论分割方法在舌像分割中的应用[J].计算机工程与应用,2012,48(5):201-203.CHEN S C,FU H G,WANG Y.Application of improved graph theory image segmentation algorithm in tongue image segmentation[J].Computer Engineering & Applications,2012,48(5):201-203(in Chinese).
[10] GUO J Y,YANG Y K,WU Q W,et al.Adaptive active contour model based automatic tongue image segmentation[C]//International Congress on Image and Signal Processing,Biomedical Engineering and Informatics,2017:1386-1390.
[11] SHI M J,LI G Z,LI F F.C²G²FSnake:Automatic tongue image segmentation utilizing prior knowledge[J].Science China:Information Sciences,2013,56(9):1-14.
[12] LIN B Q,XIE J W,LI C H.Deeptongue:Tongue segmentation via resnet[C]//IEEE International Conference on Acoustics,Speech and Signal Processing.Piscataway,NJ:IEEE Press,2018:1035-1039.
[13] KRIZHEVSKY A,SUTSKEVER I,HINTON G.ImageNet classification with deep convolutional neural networks[C]//Advances in Neural Information Processing Systems,2013:1097-1105.
[14] SIMONYAN K,ZISSERMAN A.Very deep convolutional networks for large-scale image recognition[EB/OL].(2014-09-04)[2019-01-28].https://arxiv.org/abs/1409.1556.
[15] GIRSHICK R,DONAHUE J,DARRELL T,et al.Rich feature hierarchies for accurate object detection and semantic segmentation[C]//IEEE Conference on Computer Vision and Pattern Recognition.Piscataway,NJ:IEEE Press,2014:580-587.
[16] GIRSHICK R.Fast R-CNN[C]//IEEE International Conference on Computer Vision.Piscataway,NJ:IEEE Press,2015:15801732.
[17] REN S Q,HE K M,GIRSHICK R,et al.Faster R-CNN:Towards real-time object detection with region proposal networks[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(6):1137-1149.
[18] SHELHAMER E,JONATHAN L,TREVOR D.Fully convolutional networks for semantic segmentation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(4):640-651.
[19] NOH H,HONG S,HAN B.Learning deconvolution network for semantic segmentation[C]//IEEE International Conference on Computer Vision.Piscataway,NJ:IEEE Press,2015:1520-1528.
[20] BADRINARAYANAN V,KENDALL A,CIPOLLA R.SegNet:A deep convolutional encoder-decoder architecture for image segmentation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(12):2481-2495.
[21] CHEN L C,PAPANDREOU G,KOKKINOS I,et al.DeepLab:Semantic image segmentation with deep convolutional nets,atrous convolution,and fully connected CRFs[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2018,40(4):834-848.
[22] LI J,XU B C,BAN X J.A tongue image segmentation method based on enhanced HSV convolutional neural network[C]//International Conference on Cooperative Design,Visualization and Engineering.Berlin:Springer,2017:252-260.
[23] QU P L,ZHANG H,ZHUO L,et al.Automatic tongue image segmentation for traditional Chinese medicine using deep neural network[C]//Intelligent Computing Theories and Application.Berlin:Springer,2017:247-259.
[24] HOSCHNEIDER M,KRONLAND-MARTINET R,MORLET J,et al.A real-time algorithm for signal analysis with the help of the wavelet transform[C]//Wavelets:Time-Frequency Methods Phase Space,1989:289-297.
[25] PHILIPP K,KOLTUN V.Efficient inference in fully connected CRFs with Gaussian edge potentials[J].Advances in Neural Information Processing Systems,2011,24(1):109-117.
[26] HARIHARAN B,ARBELAEZ P,BOURDEV L,et al.Semantic contours from inverse detectors[C]//IEEE International Conference on Computer Vision.Piscataway,NJ:IEEE Press,2011:991-998.
[27] RONNEBERGER O,FISCHER P,BROX T.U-net:Convolutional networks for biomedical image segmentation[C]//International Conference on Medical Image Computing and Computer-Assisted Intervention.Berlin:Springer,2015:234-241.

基于DCNN和全连接CRF的舌图像分割算法

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

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	孙宇航, 曾国奇, 刘春辉, 张多纳. 基于深度学习的无人机数据链信噪比估计算法[J]. 北京航空航天大学学报, 2019, 45(9): 1855-1863.
[2]	张克明, 蔡远文, 任元. 基于生成对抗网络的航天异常事件检测方法[J]. 北京航空航天大学学报, 2019, 45(7): 1329-1336.
[3]	魏宏喜, 张越. 基于生成对抗网络的零样本图像分类[J]. 北京航空航天大学学报, 2019, 45(12): 2345-2350.
[4]	翟宇轩, 刘怡桑, 徐艺文, 陈忠辉, 房颖, 赵铁松. 基于HTTP自适应流媒体传输的3D视频质量评价[J]. 北京航空航天大学学报, 2019, 45(12): 2456-2462.
[5]	张梦琴, 孟权令, 张维刚. 基于深度视觉语义嵌入的视频缩略图推荐[J]. 北京航空航天大学学报, 2019, 45(12): 2479-2486.
[6]	佟骏超, 吴熙林, 丁丹丹. 时空域上下文学习的视频多帧质量增强方法[J]. 北京航空航天大学学报, 2019, 45(12): 2506-2513.
[7]	贾瑞明, 刘圣杰, 李锦涛, 王赟豪, 潘海侠. 基于编解码双路卷积神经网络的视觉自定位方法[J]. 北京航空航天大学学报, 2019, 45(10): 1965-1972.
[8]	赵国, 秦世引. PMMWI与VI优势互补的人体隐蔽违禁物检测与定位[J]. 北京航空航天大学学报, 2019, 45(10): 2011-2025.
[9]	郭琳, 秦世引. 遥感图像飞机目标高效搜检深度学习优化算法[J]. 北京航空航天大学学报, 2019, 45(1): 159-173.
[10]	王俊, 郑彤, 雷鹏, 张原, 樵明朗. 基于卷积神经网络的手势动作雷达识别方法[J]. 北京航空航天大学学报, 2018, 44(6): 1117-1123.
[11]	韩京冶, 许福, 陈志泊, 刘辉. 一种基于深度学习的交互式电话号码识别方法[J]. 北京航空航天大学学报, 2018, 44(5): 1074-1080.
[12]	王鑫, 吴际, 刘超, 杨海燕, 杜艳丽, 牛文生. 基于LSTM循环神经网络的故障时间序列预测[J]. 北京航空航天大学学报, 2018, 44(4): 772-784.
[13]	车畅畅, 王华伟, 倪晓梅, 洪骥宇. 基于深度学习的航空发动机故障融合诊断[J]. 北京航空航天大学学报, 2018, 44(3): 621-628.
[14]	许轲, 吴凤鸽, 赵军锁. 基于深度强化学习的软件定义卫星姿态控制算法[J]. 北京航空航天大学学报, 2018, 44(12): 2651-2659.
[15]	黄洁, 姜志国, 张浩鹏, 姚远. 基于卷积神经网络的遥感图像舰船目标检测[J]. 北京航空航天大学学报, 2017, 43(9): 1841-1848.