基于深度学习的微观驱替图像分类

王满龙; 何小海; 龚剑; 滕奇志

doi:10.3969/j.issn.2096-6091.2023.16.003

您当前的位置：

首页 >

文章列表页 >

基于深度学习的微观驱替图像分类

研究论文 | 更新时间：2025-03-26

- 基于深度学习的微观驱替图像分类
- Microscopic Displacement Image Classification Based on Deep Learning
- 新一代信息技术 2023年6卷第16期页码：14-20
- 作者机构：
  
  1.四川大学电子信息学院，四川成都 610065
  2.成都西图科技有限公司，四川成都 610065
- 作者简介：
  
  王满龙（1999—），男，现为四川大学硕士研究生。研究方向：数字图像处理。Email：488983875@qq.com
  何小海（1964—），男，教授，现为四川大学博士生导师。研究方向：图像处理与信息系统、机器视觉与智能系统。
  滕奇志（1961—），女，教授，现为四川大学博士生导师。研究方向：图像处理与模式识别。Email：qzteng@scu.edu.cn
- 基金信息：
- DOI：10.3969/j.issn.2096-6091.2023.16.003
  中图分类号： TP391.41
- 纸质出版日期：2023-08-30
- 稿件说明：
移动端阅览
王满龙, 何小海, 龚剑, 等. 基于深度学习的微观驱替图像分类[J]. 新一代信息技术, 2023, 6(16): 14-20

WANG Man-long, HE Xiao-hai, GONG Jian, et al. Microscopic Displacement Image Classification Based on Deep Learning[J]. New Generation of Information Technology, 2023, 6(16): 14-20
王满龙, 何小海, 龚剑, 等. 基于深度学习的微观驱替图像分类[J]. 新一代信息技术, 2023, 6(16): 14-20 DOI： 10.3969/j.issn.2096-6091.2023.16.003.

WANG Man-long, HE Xiao-hai, GONG Jian, et al. Microscopic Displacement Image Classification Based on Deep Learning[J]. New Generation of Information Technology, 2023, 6(16): 14-20 DOI： 10.3969/j.issn.2096-6091.2023.16.003.

摘要

微观驱替模拟实验是研究分析驱替机理的一项重要技术，为了研究不同驱替剂的驱油效率、波及区域以及变化情况，需要对此进行分析，目前提取驱替剂的方法是利用彩色阈值分割，这需要大量人工交互且分类结果不够准确。针对这些问题，本文提出了一种基于深度学习的驱替剂分类算法，以UNet++模型为网络核心架构，它整合了不同层次的特征，在编码阶段结束时，将空洞空间金字塔结构嵌入，并且增加注意力机制来防止像素级信息的缺失，提高特征提取的准确性。通过对多组图像进行实验表明，该方法可以获得良好的分类效果。

Abstract

The microscopic displacement experiment is an essential techniques for studying and analyzing displacement mechanisms. To investigate the efficiency

coverage area

and variations of different displacement agents

accurate analysis is required. The current method of extracting displacement agents relies on manual interaction through color threshold segmentation

which is both labor-intensive and yields imprecise classification results. Addressing these issues

this paper proposes a displacement agent classification algorithm based on deep learning. The core architecture of the proposed model is UNet++

which integrates features from different hierarchical levels. At the end of the encoding phase

a spatial pyramid structure is embedded

and an attention mechanism is introduced to prevent the loss of pixel-level information

thus enhancing the accuracy of feature extraction. Experimental results on multiple sets of images demonstrate that the proposed method achieves excellent classification performance.

关键词

Keywords

references

吴伟鹏 , 侯吉瑞 , 屈鸣 , 等 . 2-D智能纳米黑卡微观驱油机理可视化实验 [J ] . 油田化学 , 2020 , 37 ( 1 ): 133 - 137 .

KRIZHEVSKY A , SUTSKEVER I , HINTON G E . ImageNet classification with deep convolutional neural networks [J ] . Communications of the ACM , 2017 , 60 ( 6 ): 84 - 90 .

SIMONYAN K , ZISSERMAN A . Very deep convolutional networks for large-scale image recognition [EB/OL ] .( 2015-04-10 )[ 2023-09-10 ] . https://arxiv.org/pdf/1409.1556.pdf https://arxiv.org/pdf/1409.1556.pdf .

SZEGEDY C , LIU W , JIA Y Q , et al . Going deeper with convolutions [C ] // Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2015 : 1 - 9 .

HE K M , ZHANG X Y , REN S Q , et al . Deep residual learning for image recognition [C ] // 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2016 .

ZHOU Z W , RAHMAN SIDDIQUEE M M , TAJBAKHSH N , et al . UNet++: A nested U-Net architecture for medical image segmentation [M ] // Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support . Cham : Springer International Publishing , 2018 : 3 - 11 .

RONNEBERGER O , FISCHER P , BROX T . U-Net: convolutional networks for biomedical image segmentation [M ] // Lecture Notes in Computer Science . Cham : Springer International Publishing , 2015 : 234 - 241 .

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 .

王超 , 王帅 , 陈晓 , 等 . 联合UNet++和多级差分模块的多源光学遥感影像对象级变化检测 [J ] . 测绘学报 , 2023 , 52 ( 2 ): 283 - 296 .

王振宇 , 王颖珊 , 毛瑾玲 , 等 . 基于Dense-UNet++的关节滑膜磁共振图像分割 [J ] . 波谱学杂志 , 2022 , 39 ( 2 ): 208 - 219 .

周晋兵 , 陈鹏 , 雷雨 , 等 . 基于自旋式Unet++网络的小麦条锈病菌夏孢子自动检测方法 [J ] . 南京农业大学学报 , 2023 , 46 ( 5 ): 1004 - 1010 .

WOO S , PARK J , LEE J Y , et al . CBAM: Convolutional block attention module [C ] // Computer Vision – ECCV 2018 . Cham : Springer International Publishing , 2018 : 3 - 19 .

LONG J , SHELHAMER E , DARRELL T . Fully convolutional networks for semantic segmentation [C ] // 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) . Piscataway : IEEE , 2015 : 3431 - 3440 .

LIAN S , LUO Z M , ZHONG Z , et al . Attention guided U-Net for accurate iris segmentation [J ] . Journal of Visual Communication and Image Representation , 2018 , 56 : 296 - 304 .

HUANG H M , LIN L F , TONG R F , et al . UNet 3 +: A full-scale connected UNet for medical image segmentation[C ] // ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) . Piscataway : IEEE , 2020 .

WANG H N , CAO P , WANG J Q , et al . UCTransNet: Rethinking the skip connections in U-net from a channel-wise perspective with transformer [J ] . Proceedings of the AAAI Conference on Artificial Intelligence , 2022 , 36 ( 3 ): 2441 - 2449 .

VALANARASU J M J , PATEL V M . UNeXt: MLP-based rapid medical image segmentation network [M ] // Lecture Notes in Computer Science . Cham : Springer , 2022 : 23 - 33 .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于DenseNet201的乳腺癌病理图像的预测研究

深度学习技术在医学影像分析中的应用与展望

真实世界超分辨率—语义分割联合框架研究

深度学习下的小样本玉米叶片病害识别研究