基于改进U-Net网络的液滴分割方法

doi:10.11896/jsjkx.210300193

计算机科学 ›› 2022, Vol. 49 ›› Issue (4): 227-232.doi: 10.11896/jsjkx.210300193

• 计算机图形学&多媒体 • 上一篇下一篇

基于改进U-Net网络的液滴分割方法

高心悦¹, 田汉民^1,2

1 河北工业大学电子信息工程学院天津 300401;
2 天津市电子材料与器件重点实验室天津 300401

收稿日期:2021-03-18 修回日期:2021-04-09 发布日期:2022-04-01
通讯作者: 田汉民(tianhanmin@hebut.edu.cn)
作者简介:(936869913@qq.com)

Droplet Segmentation Method Based on Improved U-Net Network

GAO Xin-yue¹, TIAN Han-min^1,2

1 School of Electronic and Information Engineering, Hebei University of Technology, Tianjin 300401, China;
2 Tianjin Key Laboratory of Electronic Materials and Devices, Tianjin 300401, China

Received:2021-03-18 Revised:2021-04-09 Published:2022-04-01
About author:GAO Xin-yue,born in 1996,postgra-duate.Her main research interests include deep learning and picture processing.TIAN Han-min,born in 1975,Ph.D,professor.His main research interests include picture processing and contact angle measurement.

摘要/Abstract

摘要： 液滴图像的精确分割是高精度接触角测量的重要环节,针对在液滴分割过程中存在的目标不准确、轮廓不完整以及固-液-汽3项交点和边界细节效果不佳的问题,文中提出了一种适用于液滴分割的神经网络模型。该模型以U-Net网络为基础,在其输入处加入1×1卷积层汇总图像特征,避免从初始图像中丢失信息;并采用Resnet18结构作为U-Net的特征学习编码器,增强了网络的表达能力,促进了梯度的传播。在解码过程中引入密集连接的特征融合技术,在提升分割目标细节信息的同时降低了网络参数。最后在每个卷积层后都添加批量归一化操作,进一步优化了网络性能。实验结果表明,改进的U-Net模型能够有效提高液滴识别的准确率,提升分割效果,在接触角测量领域具有一定的参考价值。

关键词: U-Net, 残差网络, 接触角测量, 特征融合, 液滴分割

Abstract: The accurate segmentation of liquid drop image is an important part of high precision contact Angle measurement.Aiming at the problems of inaccurate target, incomplete contour, and poor effect of solid-liquid-vapor intersection and boundary details in the process of liquid drop segmentation, a neural network model suitable for liquid drop segmentation is proposed.The model is based on U-Net network, and a 1×1 convolution layer is added at its input to summarize image features to avoid losing information from the initial image.Resnet18 structure is used as the feature learning encoder of U-Net to enhance the expression ability of the network and promote the propagation of gradient.The feature fusion technology of dense connection is added in the decoding process, which improves the detail information of segmented target and reduces the network parameters.Finally, a batch normalization operation is added after each convolution layer to further optimize the network performance.Experimental results show that the improved U-Net model can effectively improve the accuracy of droplet identification and segmentation effect, and has a certain reference value in the field of contact Angle measurement.

Key words: Contact angle measurement, Droplet segmentation, Feature fusion, ResNet, U-Net

中图分类号:

TP391

高心悦, 田汉民. 基于改进U-Net网络的液滴分割方法[J]. 计算机科学, 2022, 49(4): 227-232. https://doi.org/10.11896/jsjkx.210300193

GAO Xin-yue, TIAN Han-min. Droplet Segmentation Method Based on Improved U-Net Network[J]. Computer Science, 2022, 49(4): 227-232. https://doi.org/10.11896/jsjkx.210300193

参考文献

[1] ZHANG P.Study on contact angle measurement method based on image analysis technology[D].Shanghai:East China University of Science and Technology,2014.
[2] ZHAO K Y,TIAN H M,GUO D,et al.Influence of background light on high precision contact angle measurement[J].Instrument Technology and Sensors,2019(5):100-103.
[3] ZHANG T,TIAN H M,RONG X Y,et al.Application of particle swarm optimization canny operator in high precision contact angle measurement[J].Journal of Hebei University of Techno-logy,2018,47(3):30-35.
[4] WANG X H,LI J J,YANG W,et al.Image processing and detection of contact angle[J].Photoelectronic Technique,2011,31(1):14-19.
[5] ZHANG P,WAN Y Q,ZHOU Y L.A new boundary extraction algorithm and its application in contact angle measurement[J].Journal of East China University of Science and Technology(Natural Science),2014,40(6):746-751.
[6] ZHAO K Y,TIAN H M,GUO D,et al.Automatic measurement method of contact angle based on feature point detection[J].Journal of Electronic Measurement and Instrumentation,2018,32(11):147-153.
[7] ZHOU L L,JIANG F.A review of image segmentation methods[J].Computer Application Research,2017,34(7):1921-1928.
[8] LONG J,SHELHAMER E,DARRELL T.Fully convolutional networks for semantic segmentation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2015,39(4):640-651.
[9] RONNEBERGER O,FISCHER P,BROX T.U-Net:Convolu-tional networks for biomedical image segmentation [C]//International Conference on Medical Image Computing and Compu-ter-Assisted Intervention.Springer International Publishing,2015:234-241.
[10] DONG Y,FENG H J,XU Z M,et al.Attention Res-Unet:An efficient shadow detection algorithm[J].Journal of Zhejiang University (Engineering Science),2019,53(2):172-180,205.
[11] JING J,WANG Z,RÄTSCH M,et al.Mobile-Unet:An efficient convolutional neural network for fabric defect detection[J].Textile Research Journal,2020,66(5):1-17.
[12] WANG E K,CHEN C M,HASSAN M M,et al.A deep learning based medical image segmentation technique in internet-of-medical-things domain[J].Future Generation Computer Systems,2020,108:135-144.
[13] XIAO X,LIAN S,LUO Z,et al.Weighted res-unet for high-quality retina vessel segmentation[C]//2018 9th International Conference on Information Technology in Medicine and Education (ITME).IEEE Computer Society,2018.
[14] HE K,ZHANG X,REN S,et al.Deep residual learning forimage recognition[C]//IEEE Conference on Computer Vision and Pattern Recognition.Las Vegas:IEEE Computer Society,2016:770-778.
[15] HUANG G,LIU Z,MAATEN L V D,et al.Densely connected convolutional networks[C]//IEEE Conference on Computer Visionand Pattern Recognition.2017:2261-2269.
[16] ROTHER C.GrabCut:Interactive foreground extraction using iterated graph cuts[J].Acm Trans Graph,2004,23(8):309-314.
[17] BADRINARAYANAN V,KENDALL A,CIPOLLA R.Seg-Net:A deep convolutional encoder-decoder architecture for image segmentation[C]//IEEE Transactions on Pattern Analysis and Machine Intelligence.2017.

相关文章 15

[1]	王馨彤, 王璇, 孙知信. 基于多尺度记忆残差网络的网络流量异常检测模型 Network Traffic Anomaly Detection Method Based on Multi-scale Memory Residual Network 计算机科学, 2022, 49(8): 314-322. https://doi.org/10.11896/jsjkx.220200011
[2]	张颖涛, 张杰, 张睿, 张文强. 全局信息引导的真实图像风格迁移 Photorealistic Style Transfer Guided by Global Information 计算机科学, 2022, 49(7): 100-105. https://doi.org/10.11896/jsjkx.210600036
[3]	程成, 降爱莲. 基于多路径特征提取的实时语义分割方法 Real-time Semantic Segmentation Method Based on Multi-path Feature Extraction 计算机科学, 2022, 49(7): 120-126. https://doi.org/10.11896/jsjkx.210500157
[4]	高荣华, 白强, 王荣, 吴华瑞, 孙想. 改进注意力机制的多叉树网络多作物早期病害识别方法 Multi-tree Network Multi-crop Early Disease Recognition Method Based on Improved Attention Mechanism 计算机科学, 2022, 49(6A): 363-369. https://doi.org/10.11896/jsjkx.210500044
[5]	陈永平, 朱建清, 谢懿, 吴含笑, 曾焕强. 基于外接圆半径差损失的实时安全帽检测算法 Real-time Helmet Detection Algorithm Based on Circumcircle Radius Difference Loss 计算机科学, 2022, 49(6A): 424-428. https://doi.org/10.11896/jsjkx.220100252
[6]	孙洁琪, 李亚峰, 张文博, 刘鹏辉. 基于离散小波变换的双域特征融合深度卷积神经网络 Dual-field Feature Fusion Deep Convolutional Neural Network Based on Discrete Wavelet Transformation 计算机科学, 2022, 49(6A): 434-440. https://doi.org/10.11896/jsjkx.210900199
[7]	郁舒昊, 周辉, 叶春杨, 王太正. SDFA:基于多特征融合的船舶轨迹聚类方法研究 SDFA:Study on Ship Trajectory Clustering Method Based on Multi-feature Fusion 计算机科学, 2022, 49(6A): 256-260. https://doi.org/10.11896/jsjkx.211100253
[8]	杨玥, 冯涛, 梁虹, 杨扬. 融合交叉注意力机制的图像任意风格迁移 Image Arbitrary Style Transfer via Criss-cross Attention 计算机科学, 2022, 49(6A): 345-352. https://doi.org/10.11896/jsjkx.210700236
[9]	蓝凌翔, 池明旻. 基于特征注意力融合网络的遥感变化检测研究 Remote Sensing Change Detection Based on Feature Fusion and Attention Network 计算机科学, 2022, 49(6): 193-198. https://doi.org/10.11896/jsjkx.210500058
[10]	韩红旗, 冉亚鑫, 张运良, 桂婕, 高雄, 易梦琳. 基于共同子空间分类学习的跨媒体检索研究 Study on Cross-media Information Retrieval Based on Common Subspace Classification Learning 计算机科学, 2022, 49(5): 33-42. https://doi.org/10.11896/jsjkx.210200157
[11]	范新南, 赵忠鑫, 严炜, 严锡君, 史朋飞. 结合注意力机制的多尺度特征融合图像去雾算法 Multi-scale Feature Fusion Image Dehazing Algorithm Combined with Attention Mechanism 计算机科学, 2022, 49(5): 50-57. https://doi.org/10.11896/jsjkx.210400093
[12]	李发光, 伊力哈木·亚尔买买提. 基于改进CenterNet的航拍绝缘子缺陷实时检测模型 Real-time Detection Model of Insulator Defect Based on Improved CenterNet 计算机科学, 2022, 49(5): 84-91. https://doi.org/10.11896/jsjkx.210400142
[13]	董奇达, 王喆, 吴松洋. 结合注意力机制与几何信息的特征融合框架 Feature Fusion Framework Combining Attention Mechanism and Geometric Information 计算机科学, 2022, 49(5): 129-134. https://doi.org/10.11896/jsjkx.210300180
[14]	赵人行, 徐频捷, 刘瑶. 基于深度卷积残差网络的心电单导联房颤检测方法 ECG-based Atrial Fibrillation Detection Based on Deep Convolutional Residual Neural Network 计算机科学, 2022, 49(5): 186-193. https://doi.org/10.11896/jsjkx.220200002
[15]	李鹏祖, 李瑶, Ibegbu Nnamdi JULIAN, 孙超, 郭浩, 陈俊杰. 基于多特征融合的重叠组套索脑功能超网络构建及分类 Construction and Classification of Brain Function Hypernetwork Based on Overlapping Group Lasso with Multi-feature Fusion 计算机科学, 2022, 49(5): 206-211. https://doi.org/10.11896/jsjkx.210300049

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

基于改进U-Net网络的液滴分割方法

Droplet Segmentation Method Based on Improved U-Net Network

PDF (PC)

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

Metrics

本文评价

推荐阅读 0