用深度学习自动分析聚合物多孔材料结构，秒级完成人工需数小时的工作。
On the use of neural networks for the structural characterization of polymeric porous materials
- 基于改进的Mask R-CNN模型，实现多孔材料图像的自动分割与分析。
- 在4个数据集上达到与人工标注相当的精度，处理时间从小时级降至秒级。
- 适合材料科学领域研究人员快速获取多孔结构定量参数。
多孔材料的结构表征是研究中的关键任务，需评估包含数百个孔洞的图像，现有方法耗时长且易受人为误差和主观性影响。本文研究一种基于深度学习的自动表征技术，采用卷积神经网络对四组不同聚合物多孔材料（闭孔挤出聚苯乙烯XPS、聚氨酯PU、聚甲基丙烯酸甲酯PMMA及开孔聚氨酯）的大量SEM图像进行分析。通过多个微调后的Mask R-CNN模型在不同训练配置下的评估，结果表明该工具可在数秒内实现与耗时的人工方法相当的高精度结果，显著提升效率与可重复性。
原文摘要 · Abstract (English)
The structural characterization is an essential task in the study of porous materials. To achieve reliable results, it requires to evaluate images with hundreds of pores. Current methods require large time amounts and are subjected to human errors and subjectivity. A completely automatic tool would not only speed up the process but also enhance its reliability and reproducibility. Therefore, the main objective of this article is the study of a deep-learning-based technique for the structural characterization of porous materials, through the use of a convolutional neural network. Several fine-tuned Mask R CNN models are evaluated using different training configurations in four separate datasets each composed of numerous SEM images of diverse polymeric porous materials: closed-pore extruded polystyrene (XPS), polyurethane (PU), and poly(methyl methacrylate) (PMMA), and open-pore PU. Results prove the tool capable of providing very accurate results, equivalent to those achieved by time consuming manual methods, in a matter of seconds.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。