arXiv subjects

Max Frei

Publications and source records attributed to Max Frei.

4 recordsLinked to original sources

arXiv2021

Characterizing soot in TEM images using a convolutional neural network

Soot is an important material with impacts that depend on particle morphology. Transmission electron microscopy (TEM) represents one of the most direct routes to qualitatively assess particle characteristics. However, producing quantitative information requires robust image processing tools, which is complicated by the low image contrast and complex aggregated morphologies characteristic of soot. The current work presents a new convolutional neural network explicitly trained to characterize soot, using pre-classified images of particles from a natural gas engine; a laboratory gas flare; and a marine engine. The results are compared against other existing classifiers before considering the effect that the classifiers have on automated primary particle size methods. Estimates of the overall uncertainties between fully automated approaches of aggregate characterization range from 25% in d_{p,100} to 85% in D_{TEM}. A consistent correlation is observed between projected-area equivalent diameter and primary particle size across all of the techniques.

physics.app-ph↗

arXiv2020

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

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.

cs.CV↗

arXiv2019

Image-Based Size Analysis of Agglomerated and Partially Sintered Particles via Convolutional Neural Networks

There is a high demand for fully automated methods for the analysis of primary particle size distributions of agglomerated, sintered or occluded primary particles, due to their impact on material properties. Therefore, a novel, deep learning-based, method for the detection of such primary particles was proposed and tested, which renders a manual tuning of analysis parameters unnecessary. As a specialty, the training of the utilized convolutional neural networks was carried out using only synthetic images, thereby avoiding the laborious task of manual annotation and increasing the ground truth quality. Nevertheless, the proposed method performs excellent on real world samples of sintered silica nanoparticles with various sintering degrees and varying image conditions. In a direct comparison, the proposed method clearly outperforms two state-of-the-art methods for automated image-based particle size analysis (Hough transformation and the ImageJ ParticleSizer plug-in), thereby attaining human-like performance.

cs.CV↗

arXiv2018

Fully automated primary particle size analysis of agglomerates on transmission electron microscopy images via artificial neural networks

There is a high demand for fully automated methods for the analysis of primary particle size distributions of agglomerates on transmission electron microscopy images. Therefore, a novel method, based on the utilization of artificial neural networks, was proposed, implemented and validated. The training of the artificial neural networks requires large quantities (up to several hundreds of thousands) of transmission electron microscopy images of agglomerates consisting of primary particles with known sizes. Since the manual evaluation of such large amounts of transmission electron microscopy images is not feasible, a synthesis of lifelike transmission electron microscopy images as training data was implemented. The proposed method can compete with state-of-the-art automated imaging particle size methods like the Hough transformation, ultimate erosion and watershed transformation and is in some cases even able to outperform these methods. It is however still outperformed by the manual analysis.

cs.CV↗