Détail de l'auteur
Auteur Mohammad Ebadi |
Documents disponibles écrits par cet auteur (1)
![](./images/expand_all.gif)
![](./images/collapse_all.gif)
![Tris disponibles](./images/orderby_az.gif)
Deep learning in denoising of micro-computed tomography images of rock samples / Mikhail Sidorenko in Computers & geosciences, vol 151 (June 2021)
![]()
[article]
Titre : Deep learning in denoising of micro-computed tomography images of rock samples Type de document : Article/Communication Auteurs : Mikhail Sidorenko, Auteur ; Denis Orlov, Auteur ; Mohammad Ebadi, Auteur ; et al., Auteur Année de publication : 2021 Article en page(s) : n° 104716 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image
[Termes IGN] accentuation d'image
[Termes IGN] apprentissage profond
[Termes IGN] classification dirigée
[Termes IGN] classification par réseau neuronal convolutif
[Termes IGN] filtrage du bruit
[Termes IGN] filtre passe-bande
[Termes IGN] roche
[Termes IGN] tomographieRésumé : (auteur) Nowadays, the advantages of Digital Rock Physics (DRP) are well known and widely applied in comprehensive core analysis. It is also known that the quality of the 3D pore scale model drastically influences the results of rock properties simulation, which makes the preprocessing stage of DRP very important. In this work, we consider the application of Deep Convolutional Neural Networks (CNNs) for the preprocessing of CT images, specifically for denoising, in two setups - conventional fully-supervised learning and the self-supervised learning, when the only available data is the noisy images. To train CNNs in a supervised setup, we use images processed by a combination of bilateral and bandpass filters. We trained CNNs of the same architecture with different loss functions to find out how the choice of a loss function influences the model's performance. Some of the obtained CNNs yielded the highest quality in terms of full-reference and no-reference metrics and significant histogram effect (bimodal intensity distribution). Images denoised with these models were qualitatively and quantitatively better than the reference “ground truth” images used for training. We use the Deep Image Prior algorithm to train denoising models in a self-supervised setup. The obtained models are much better than ones obtained in fully-supervised setup, but are too slow, as they are optimization-based rather than feed-forward. Such an algorithm can be used in the dataset generation for feed-forward meta-models. These results could help to develop an AI-based instrument to build high-quality 3D segmented models of rocks for DRP applications. Numéro de notice : A2021-389 Affiliation des auteurs : non IGN Thématique : IMAGERIE/INFORMATIQUE Nature : Article DOI : 10.1016/j.cageo.2021.104716 Date de publication en ligne : 02/03/2021 En ligne : https://doi.org/10.1016/j.cageo.2021.104716 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97672
in Computers & geosciences > vol 151 (June 2021) . - n° 104716[article]