Přístupnostní navigace
E-application
Search Search Close
Publication detail
SIKORA, P. KIAC, M. COSTA, P. MOLINERO-GARCÍA, A. GORSKA, M.
Original Title
Automatic image analysis applied to the recognition of quartz surface microtextures using neural network
Type
journal article in Web of Science
Language
English
Original Abstract
Microtextures imprinted on the surface of quartz grains provide in-depth information on the environmental conditions and sedimentary processes that affected the study sediments. Microtextural analyses are therefore widely used in the provenance studies of sediments. In order to minimize the subjectivity of microtextural recognition, we propose a new software, called DeepGrain (source codes are available at https://github.com/d eepgrains/deepgrain), for the automatic identification of microtextures on the surface of quartz grains using the DeepLabV3 model with applied improving techniques. The approach provides an accuracy of 99 % of the area of the tested grains and 63 % of the mechanical features on the surfaces of the tested grains. The inference of a single SEM image of quartz grain took an average of 3.10 sec, leading to a significant reduction in the analysis time of a single grain.
Keywords
Artificial intelligence; Machine learning; Segmentation; SEM; Quartz microtextures; DeepGrain
Authors
SIKORA, P.; KIAC, M.; COSTA, P.; MOLINERO-GARCÍA, A.; GORSKA, M.
Released
24. 4. 2024
Publisher
PERGAMON-ELSEVIER SCIENCE LTD
Location
OXFORD
ISBN
1878-4291
Periodical
MICRON
Year of study
182
Number
July 2024
State
United Kingdom of Great Britain and Northern Ireland
Pages from
1
Pages to
10
Pages count
URL
https://www.sciencedirect.com/science/article/pii/S0968432824000556?via%3Dihub
BibTex
@article{BUT188880, author="Pavel {Sikora} and Martin {Kiac} and Pedro J.M. {Costa} and Alberto {Molinero-García} and Martyna E. {Gorska}", title="Automatic image analysis applied to the recognition of quartz surface microtextures using neural network", journal="MICRON", year="2024", volume="182", number="July 2024", pages="1--10", doi="10.1016/j.micron.2024.103638", issn="1878-4291", url="https://www.sciencedirect.com/science/article/pii/S0968432824000556?via%3Dihub" }