FibeR-CNN: Expanding Mask R-CNN to Improve Image-Based Fiber Analysis

TL;DR

FibeR-CNN is a novel neural network architecture that enhances fiber analysis in images by combining existing R-CNN models and adding new prediction heads, significantly improving accuracy over standard Mask R-CNN.

Contribution

The paper introduces FibeR-CNN, a new architecture that integrates Mask and Keypoint R-CNNs with additional heads for fiber-specific measurements, advancing automated fiber analysis.

Findings

FibeR-CNN surpasses Mask R-CNN by 33% in mean average precision.

The model accurately predicts fiber widths and lengths.

Validation on a novel fiber image dataset demonstrates improved performance.

Abstract

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.