Automatic image analysis applied to the recognition of quartz surface microtextures using neural network

被引：0

作者：

Sikora, Pavel ^{[1
]}

Kiac, Martin ^{[1
]}

Costa, Pedro J. M. ^{[2
,3
]}

Molinero-Garcia, Alberto ^{[4
,5
]}

Gorska, Martyna E. ^{[6
]}

机构：

[1] Brno Univ Technol, Fac Elect Engn & Commun, Dept Telecommun, Technicka 12, Brno 616 00, Czech Republic

[2] Univ Coimbra, Fac Sci & Technol, Dept Earth Sci, Edificio Cent,Rua Silvio Lima, P-3030790 Coimbra, Portugal

[3] Univ Lisbon, Fac Sci, Inst Dom Luiz, Edificio C1, P-1749016 Lisbon, Portugal

[4] Univ Huelva, Dept Earth Sci, Campus El Carmen, Huelva 21071, Spain

[5] Univ Huelva, Res Ctr Nat Resources Hlth & Environm RENSMA, Campus El Carmen, Huelva 21071, Spain

[6] Nicolaus Copernicus Univ Torun, Fac Earth Sci & Spatial Management, Lwowska 1, PL-87100 Torun, Poland

来源：

MICRON | 2024年 / 182卷

关键词：

Artificial intelligence; Machine learning; Segmentation; SEM; Quartz microtextures; DeepGrain; GRAINS; MICROMORPHOLOGY; SEM;

D O I：

10.1016/j.micron.2024.103638

中图分类号：

TH742 [显微镜];

学科分类号：

摘要：

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.

引用

页数：10

共 50 条

[21] Comparison of cephalometric measurements between conventional and automatic cephalometric analysis using convolutional neural network [J].

Jeon, Sangmin ;

Lee, Kyungmin Clara .

PROGRESS IN ORTHODONTICS, 2021, 22 (01)

[22] The Image Recognition Based on Neural Network and Bayesian Decision [J].

Wang, Chugege .

ADVANCES IN MATERIALS, MACHINERY, ELECTRONICS II, 2018, 1955

[23] A Survey on Image Classification and Activity Recognition using Deep Convolutional Neural Network Architecture [J].

Sornam, M. ;

Muthusubash, Kavitha ;

Vanitha, V. .

2017 NINTH INTERNATIONAL CONFERENCE ON ADVANCED COMPUTING (ICOAC), 2017, :121-126

[24] Smart license plate recognition system based on image processing using neural network [J].

Koval, V ;

Turchenko, V ;

Kochan, V ;

Sachenko, A ;

Markowsky, G .

IDAACS'2003: PROCEEDINGS OF THE SECOND IEEE INTERNATIONAL WORKSHOP ON INTELLIGENT DATA ACQUISITION AND ADVANCED COMPUTING SYSTEMS: TECHNOLOGY AND APPLICATIONS, 2003, :123-127

[25] Identification of Microrecording Artifacts with Wavelet Analysis and Convolutional Neural Network: An Image Recognition Approach [J].