基于深度学习的虚拟边界检测方法

doi:10.11772/j.issn.1001-9081.2018041347

计算机应用 ›› 2018, Vol. 38 ›› Issue (11): 3211-3215.DOI: 10.11772/j.issn.1001-9081.2018041347

• 第七届中国数据挖掘会议(CCDM 2018) • 上一篇下一篇

基于深度学习的虚拟边界检测方法

赖传滨¹, 韩越兴^1,2, 顾辉^3,4, 王冰¹

1. 上海大学计算机工程与科学学院, 上海 200444;
2. 上海大学上海先进通信与数据科学研究院, 上海 200444;
3. 上海大学材料基因组工程研究院, 上海 200444;
4. 上海大学材料科学与工程学院, 上海 200444

收稿日期:2018-04-30 修回日期:2018-06-25 出版日期:2018-11-10 发布日期:2018-11-10
通讯作者: 韩越兴
作者简介:赖传滨(1994-),男,江西赣州人,硕士研究生,主要研究方向:材料图像处理、计算机视觉、机器学习;韩越兴(1975-),男,黑龙江海伦人,讲师,博士,主要研究方向:材料图像处理、分子机器人、计算机视觉、机器视觉;顾辉(1963-),男,江苏如皋人,教授,博士,主要研究方向:先进材料分层的相-微观结构-界面关系、微观结构的定量分析方法;王冰(1978-),女,山东掖县人,教授,博士,主要研究方向:复杂网络、鲁棒网络结构、网络同步性设计。
基金资助:
国家青年科学基金资助项目（61603237）；上海市浦江人才计划项目（17PJ1402900）；上海高校特聘教授（东方学者）岗位计划。

Novel virtual boundary detection method based on deep learning

LAI Chuanbin¹, HAN Yuexing^1,2, GU Hui^3,4, WANG Bing¹

1. School of Computer Engineering and Science, Shanghai University, Shanghai 200444, China;
2. Shanghai Institute for Advanced Communication and Data Science, Shanghai University, Shanghai 200444, China;
3. Material Genome Institute, Shanghai University, Shanghai 200444, China;
4. School of Materials Science and Engineering, Shanghai University, Shanghai 200444, China

Received:2018-04-30 Revised:2018-06-25 Online:2018-11-10 Published:2018-11-10
Supported by:
This work is partially supported by the National Science Foundation for Young Scientists of China (61603237), the Shanghai Pujiang Program (17PJ1402900), the Program for Professor of Special Appointment (Eastern Scholar) at at Shanghai Institutions of Higher Learning.

摘要/Abstract

摘要： 针对传统边缘检测方法无法对材料微观图像中不同区域间存在的"虚拟边界"（VB）进行准确检测的问题，提出一种基于卷积神经网络（CNN）的虚拟边界检测模型，称之为"虚拟边界网络"（VBN）。该模型对VGGNet深度学习模型进行了简化，并在模型训练过程中采用了dropout以及Adam算法等优化策略。VBN以图像中每个像素为中心所取的图像块作为输入，然后输出该图像块所属的类别并据此判断中心像素是否属于虚拟边界。在对两类材料图像进行虚拟边界检测的实验中，VBN的平均检测精度到达92.5%，平均召回率达到89.5%，证明该模型能够准确、有效地对图像中的虚拟边界进行检测，是一种替代低效率人工分析方法的有效手段。

关键词: 虚拟边界检测, 边缘检测, 卷积神经网络, 深度学习, 图像分割

Abstract: Traditional edge detection methods can not accurately detect the Virtual Boundary (VB) between different regions in materials microscopic images. In order to solve this problem, a virtual boundary detection model based on Convolutional Neural Network (CNN) called Virtual Boundary Net (VBN) was proposed. The VGGNet (Visual Geometry Group Net) deep learning model was simplified, and dropout and Adam algorithms were applied in the training process. An image patch centered on each pixel in the image was extracted as the input, and the class of the image patch was output to decide whether the center pixel belongs to the virtual boundary or not. In the experiment of virtual boundary detection for two kinds of material images, the average detection precision of this method reached 92.5%, and the average recall rate reached 89.5%. The experimental results prove that the VBN can detect the virtual boundary in the image accurately and effectively, which is an alternative method to low-efficient manual analysis.

Key words: virtual boundary detection, edge detection, Convolutional Neural Network (CNN), deep learning, image segmentation

中图分类号:

TP399

赖传滨, 韩越兴, 顾辉, 王冰. 基于深度学习的虚拟边界检测方法[J]. 计算机应用, 2018, 38(11): 3211-3215.

LAI Chuanbin, HAN Yuexing, GU Hui, WANG Bing. Novel virtual boundary detection method based on deep learning[J]. Journal of Computer Applications, 2018, 38(11): 3211-3215.

参考文献

[1] KORNIY V, RUSYN B, LYSAK Y, et al. Quantitative analysis of metallographic images[C]//Proceedings of the 2006 International Conference on Modern Problems of Radio Engineering, Telecommunications, and Computer Science. Piscataway, NJ:IEEE, 2006:251-252.
[2] 邓仕超, 刘铁根, 萧泽新. 应用Canny算法和灰度等高线的金相组织封闭边缘提取[J]. 光学精密工程, 2010, 18(10):2314-2323.(DENG S C, LIU T G, XIAO Z X. Extraction of enclosing image edge for metallographic structure based on Canny and grayscale contour line[J]. Optics and Precision Engineering, 2010, 18(10):2314-2323.)
[3] KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet classification with deep convolutional neural networks[C]//Proceedings of the 2012 International Conference on Neural Information Processing Systems. Lake Tahoe, Nevada:Curran Associates Inc., 2012:1097-1105.
[4] LECUN Y, BOTTOU L, BENGIO Y, et al. Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE, 1998, 86(11):2278-2324.
[5] SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[EB/OL].[2018-03-20].http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.740.6937&rep=rep1&type=pdf.
[6] MUTHUKRISHNAN. R, RADHA M. Edge detection techniques for image segmentation[J]. International Journal of Computer Science & Information Technology, 2012, 3(6):250-254.
[7] CANNY J. A computational approach to edge detection[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 1987, 8(6):184-203.
[8] MARTIN D R, FOWLKES C C, MALIK J. Learning to detect natural image boundaries using local brightness, color, and texture cues[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2004, 26(5):530-549.
[9] DOLLAR P, ZITNICK C L. Structured forests for fast edge detection[C]//Proceedings of the 2013 IEEE International Conference on Computer Vision. Washington, DC:IEEE Computer Society, 2014:1841-1848.
[10] LIM J J, ZITNICK C L, DOLLAR P. Sketch tokens:a learned mid-level representation for contour and object detection[C]//Proceedings of the 2013 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2013:3158-3165.
[11] GANIN Y, LEMPITSKY V. N⁴-Fields:neural network nearest neighbor fields for image transforms[C]//ACCV 2014:Asian Conference on Computer Vision. Berlin:Springer, 2014:536-551.
[12] BERTASIUS G, SHI J, TORRESANI L. DeepEdge:a multi-scale bifurcated deep network for top-down contour detection[C]//Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2015:4380-4389.
[13] SHEN W, WANG X, WANG Y, et al. DeepContour:a deep convolutional feature learned by positive-sharing loss for contour detection[C]//Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2015:3982-3991.
[14] ANANYEV M, GAVRILYUK A, MITRI S, et al. Cu and Gd co-doped BaCeO3, proton conductors:Experimental vs SEM image algorithmic-segmentation results[J]. Electrochimica Acta, 2014, 125(12):371-379.
[15] LOPEZ P, LIRA J, HEIN I. Discrimination of ceramic types using digital image processing by means of morphological filters[J]. Archaeometry, 2014, 57(1):146-162.
[16] HAHA M B, GALLUCCI E, GUIDOUM A, et al. Relation of expansion due to alkali silica reaction to the degree of reaction measured by SEM image analysis[J]. Cement & Concrete Research, 2007, 37(8):1206-1214.
[17] 赵曌, 丁广太, 樊明磊,等. 融合LBP纹理和局部灰度特征的材料图像分割[J]. 计算机技术与发展, 2016, 26(10):11-16.(ZHAO Z, DING G T, FAN M L, et al. Material image segmentation combined LBP texture and local gray level feature[J]. Computer Technology and Development, 2016, 26(10):11-16.)
[18] CHEN Y, CHEN J. A watershed segmentation algorithm based on ridge detection and rapid region merging[C]//Proceedings of the 2014 IEEE International Conference on Signal Processing, Communications and Computing. Piscataway, NJ:IEEE, 2014:420-424.
[19] AZIMI S M, BRITZ D, ENGSTLER M, et al. Advanced steel microstructural classification by deep learning methods[EB/OL].[2018-03-20].http://pubman.mpdl.mpg.de/pubman/item/escidoc:2460757:2/component/escidoc:2460756/arXiv:1706.06480.pdf.
[20] SRIVASTAVA N, HINTON G, KRIZHEVSKY A, et al. Dropout:a simple way to prevent neural networks from overfitting[J]. Journal of Machine Learning Research, 2014, 15(1):1929-1958.
[21] KINGMA D P, BA J. Adam:a method for stochastic optimization[EB/OL].[2018-03-20].http://yeolab.weebly.com/uploads/2/5/5/0/25509700/a_method_for_stochastic_optimization_.pdf.

基于深度学习的虚拟边界检测方法

Novel virtual boundary detection method based on deep learning

PDF

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

[1]	陈成瑞, 孙宁, 何世彪, 廖勇. 面向C-V2X通信的基于深度学习的联合信道估计与均衡算法[J]. 计算机应用, 2021, 41(9): 2687-2693.
[2]	王贺兵, 张春梅. 基于非对称卷积-压缩激发-次代残差网络的人脸关键点检测[J]. 计算机应用, 2021, 41(9): 2741-2747.
[3]	郑志强, 胡鑫, 翁智, 王雨禾, 程曦. 基于改进DenseNet的牛眼图像特征提取方法[J]. 计算机应用, 2021, 41(9): 2780-2784.
[4]	宋中山, 梁家锐, 郑禄, 刘振宇, 帖军. 基于双向门控尺度特征融合的遥感场景分类[J]. 计算机应用, 2021, 41(9): 2726-2735.
[5]	李康康, 张静. 基于注意力机制的多层次编码和解码的图像描述模型[J]. 计算机应用, 2021, 41(9): 2504-2509.
[6]	张永斌, 常文欣, 孙连山, 张航. 基于字典的域名生成算法生成域名的检测方法[J]. 计算机应用, 2021, 41(9): 2609-2614.
[7]	赵宏, 孔东一. 图像特征注意力与自适应注意力融合的图像内容中文描述[J]. 计算机应用, 2021, 41(9): 2496-2503.
[8]	徐江浪, 李林燕, 万新军, 胡伏原. 结合目标检测的室内场景识别方法[J]. 计算机应用, 2021, 41(9): 2720-2725.
[9]	牟长宁, 王海鹏, 周丕宇, 侯鑫行. 基于图卷积神经网络的串联质谱从头测序[J]. 计算机应用, 2021, 41(9): 2773-2779.
[10]	谢德峰, 吉建民. 融入句法感知表示进行句法增强的语义解析[J]. 计算机应用, 2021, 41(9): 2489-2495.
[11]	代雨柔, 杨庆, 张凤荔, 周帆. 基于自监督学习的社交网络用户轨迹预测模型[J]. 计算机应用, 2021, 41(9): 2545-2551.
[12]	杨瑞, 钱晓军, 孙振强, 许振. 自然场景下多区域特征融合的混合航拍图像分割算法[J]. 计算机应用, 2021, 41(8): 2445-2452.
[13]	何正海, 线岩团, 王蒙, 余正涛. 融合句法指导与字符注意力机制的案情阅读理解方法[J]. 计算机应用, 2021, 41(8): 2427-2431.
[14]	曹玉红, 徐海, 刘荪傲, 王紫霄, 李宏亮. 基于深度学习的医学影像分割研究综述[J]. 计算机应用, 2021, 41(8): 2273-2287.
[15]	秦斌斌, 彭良康, 卢向明, 钱江波. 司机分心驾驶检测研究进展[J]. 计算机应用, 2021, 41(8): 2330-2337.