FibeR-CNN: Expanding Mask R-CNN to improve image-based fiber analysis
FibeR-CNN: Expanding Mask R-CNN to improve image-based fiber analysis
复制标题
DOI：
10.1016/j.powtec.2020.08.034
复制
发表时间：
2021-01-02
影响因子：
5.2
通讯作者：
Kruis, F. E.
中科院分区：
文献类型：
--
作者：
Frei, M.;Kruis, F. E.
纤维状材料(例如碳纳米管)具有很大的相关性，因为它们具有独特的性质，但也可能带来健康风险。不幸的是，基于图像的纤维分析仍然涉及人工标注，这是一个耗时且昂贵的过程。因此，我们建议使用基于区域的卷积神经网络(R-CNN)来自动化这一任务。MASK R-CNN是语义分割任务中使用最广泛的R-CNN，在分析纤维状物体时容易出错。为此，提出了一种新的体系结构--光纤CNN，并对其进行了验证。Fibre-CNN结合了两个成熟的R-CNN架构(MASK和Keypoint R-CNN)，并增加了用于预测纤维宽度和长度的额外网络头。因此，在一组新的纤维图像测试数据集上，Fibre-CNN能够超过MASK R-CNN的平均精度33%(11个百分点)。(C)2020爱思唯尔B.V.保留所有权利。
Fiber-shaped materials (e.g. carbon nano tubes) are of great relevance, due to their unique properties but also the health risk they can impose. Unfortunately, image-based analysis of fibers still involves manual annotation, which is a time-consuming and costly process.We therefore propose the use of region-based convolutional neural networks (R-CNNs) to automate this task. Mask R-CNN, the most widely used R-CNN for semantic segmentation tasks, is prone to errors when it comes to the analysis of fiber-shaped objects. Hence, a new architecture - FibeR-CNN - is introduced and validated. FibeR-CNN combines two established R-CNN architectures (Mask and Keypoint R-CNN) and adds additional network heads for the prediction of fiber widths and lengths. As a result, FibeR-CNN is able to surpass the mean average precision of Mask R-CNN by 33% (11 percentage points) on a novel test data set of fiber images. (C) 2020 Elsevier B.V. All rights reserved.