FibeR-CNN: Expanding Mask R-CNN to Improve Image-Based Fiber Analysis
This work addresses the time-consuming and costly manual annotation process for fiber-shaped materials like carbon nanotubes, offering an incremental improvement in automation for domain-specific applications.
The paper tackled the problem of automating image-based fiber analysis, which previously required manual annotation, by proposing FibeR-CNN, a new architecture that combines Mask and Keypoint R-CNN with additional heads for fiber width and length prediction, resulting in a 33% improvement in mean average precision over Mask R-CNN on a novel test dataset.
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.