摘要
针对采用深度学习方法提取结冰显微图像中的气泡需要大量标注数据,但人工标注气泡任务较为困难的问题,提出了一种基于风格迁移网络CycleGAN和图像分割网络Attention U-Net的域适应提取方法。该方法通过程序模拟气泡形态生成的图像为源域,结冰显微图像为目标域,通过CycleGAN将源域图像转为目标域风格,采用风格转换后的源域数据集训练Attention U-Net网络。通过对比实验对无标注结冰图像和少量标注图像两种情况进行验证。实验结果表明,在无标注图像的情况下,可实现无监督的结冰显微图像的气泡提取;在只有少量标注图像的情况下,该方法可实现更精确的气泡提取。
The extraction of bubbles from ice micrographs using deep learning methods requires a significant amount of annotated data.However,the manual annotation of bubbles presents a significant challenge in this regard.A domain-adaptive extraction method is proposed,which utilizes the CycleGAN style transfer network and the Attention U-Net image segmentation network.In this method,the image generated by simulating the shape of the bubble is used as the source domain,and the icing microscopic image is used as the target domain.The source domain image is converted into the target domain style through CycleGAN,and the Attention U-Net network is trained using the style-converted source domain dataset.The two cases of unlabeled icing images and a few labeled images are verified by comparative experiments.Experimental results show that the unsupervised extraction of air bubbles from icing microscopic images can be achieved without annotated images,and the method can achieve more accurate air bubble extraction with only a few annotated images.
作者
赵红梅
彭博
周志宏
易贤
ZHAO Hongmei;PENG Bo;ZHOU Zhihong;YI Xian(School of Computer Science,Southwest Petroleum University,Chengdu 610050,China;School of Architecture and Environment,Sichuan University,Chengdu 610041,China;State Key Laboratory of Aerodynamics,China Aerodynamics Research and Development Center,Mianyang 621050,China)
出处
《南京航空航天大学学报》
CAS
CSCD
北大核心
2024年第2期291-299,共9页
Journal of Nanjing University of Aeronautics & Astronautics
基金
国家自然科学基金重点基金(12132019)
国家重大科技专项(J2019-III-0010-0054)
国家自然科学基金面上基金(12172372)。
