On the use of neural networks for the structural characterization of polymeric porous materials

TL;DR

This paper explores a deep learning approach using Mask R CNN models to automatically and accurately analyze SEM images of polymeric porous materials, significantly reducing analysis time and human error.

Contribution

It introduces a novel application of fine-tuned Mask R CNN models for automated structural characterization of diverse porous polymers.

Findings

High accuracy comparable to manual methods

Rapid analysis in seconds

Effective across multiple polymer types

Abstract

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.