Image-Based Size Analysis of Agglomerated and Partially Sintered Particles via Convolutional Neural Networks. Frei, M. & Kruis, F. E. arXiv, July, 2019. 00000 tex.ids: FreiImageBasedSizeAnalysis2020 arXiv: 1907.05112![Image-Based Size Analysis of Agglomerated and Partially Sintered Particles via Convolutional Neural Networks [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper abstract bibtex 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.
@article{frei_image-based_2019,
title = {Image-{Based} {Size} {Analysis} of {Agglomerated} and {Partially} {Sintered} {Particles} via {Convolutional} {Neural} {Networks}},
url = {https://ui.adsabs.harvard.edu/abs/2019arXiv190705112F/abstract},
abstract = {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.},
language = {en},
urldate = {2019-12-28},
journal = {arXiv},
author = {Frei, Max and Kruis, Frank Einar},
month = jul,
year = {2019},
note = {00000
tex.ids: FreiImageBasedSizeAnalysis2020
arXiv: 1907.05112},
keywords = {Computer Science - Computer Vision and Pattern Recognition, ⛔ No DOI found},
pages = {arXiv:1907.05112},
}
Downloads: 0
{"_id":"adAd636dYtDKxHEpY","bibbaseid":"frei-kruis-imagebasedsizeanalysisofagglomeratedandpartiallysinteredparticlesviaconvolutionalneuralnetworks-2019","author_short":["Frei, M.","Kruis, F. E."],"bibdata":{"bibtype":"article","type":"article","title":"Image-Based Size Analysis of Agglomerated and Partially Sintered Particles via Convolutional Neural Networks","url":"https://ui.adsabs.harvard.edu/abs/2019arXiv190705112F/abstract","abstract":"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.","language":"en","urldate":"2019-12-28","journal":"arXiv","author":[{"propositions":[],"lastnames":["Frei"],"firstnames":["Max"],"suffixes":[]},{"propositions":[],"lastnames":["Kruis"],"firstnames":["Frank","Einar"],"suffixes":[]}],"month":"July","year":"2019","note":"00000 tex.ids: FreiImageBasedSizeAnalysis2020 arXiv: 1907.05112","keywords":"Computer Science - Computer Vision and Pattern Recognition, ⛔ No DOI found","pages":"arXiv:1907.05112","bibtex":"@article{frei_image-based_2019,\n\ttitle = {Image-{Based} {Size} {Analysis} of {Agglomerated} and {Partially} {Sintered} {Particles} via {Convolutional} {Neural} {Networks}},\n\turl = {https://ui.adsabs.harvard.edu/abs/2019arXiv190705112F/abstract},\n\tabstract = {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.},\n\tlanguage = {en},\n\turldate = {2019-12-28},\n\tjournal = {arXiv},\n\tauthor = {Frei, Max and Kruis, Frank Einar},\n\tmonth = jul,\n\tyear = {2019},\n\tnote = {00000\ntex.ids: FreiImageBasedSizeAnalysis2020\narXiv: 1907.05112},\n\tkeywords = {Computer Science - Computer Vision and Pattern Recognition, ⛔ No DOI found},\n\tpages = {arXiv:1907.05112},\n}\n\n","author_short":["Frei, M.","Kruis, F. E."],"key":"frei_image-based_2019","id":"frei_image-based_2019","bibbaseid":"frei-kruis-imagebasedsizeanalysisofagglomeratedandpartiallysinteredparticlesviaconvolutionalneuralnetworks-2019","role":"author","urls":{"Paper":"https://ui.adsabs.harvard.edu/abs/2019arXiv190705112F/abstract"},"keyword":["Computer Science - Computer Vision and Pattern Recognition","⛔ No DOI found"],"metadata":{"authorlinks":{}}},"bibtype":"article","biburl":"https://bibbase.org/zotero/ricounet67","dataSources":["rx3H6duFmTt3xD5yy"],"keywords":["computer science - computer vision and pattern recognition","⛔ no doi found"],"search_terms":["image","based","size","analysis","agglomerated","partially","sintered","particles","via","convolutional","neural","networks","frei","kruis"],"title":"Image-Based Size Analysis of Agglomerated and Partially Sintered Particles via Convolutional Neural Networks","year":2019}