Race against the Machine: can deep learning recognize microstructures as well as the trained human eye?

被引：23

作者：

Larmuseau, Michiel ^{[1
,2
,3
]}

Sluydts, Michael ^{[1
,2
]}

Theuwissen, Koenraad ^{[4
]}

Duprez, Lode ^{[4
]}

Dhaene, Tom ^{[3
]}

Cottenier, Stefaan ^{[1
,2
]}

机构：

[1] Univ Ghent, Ctr Mol Modeling, Technol Pk 46, B-9052 Zwijnaarde, Belgium

[2] Univ Ghent, Dept Electromech, Technol Pk 46, B-9052 Zwijnaarde, Belgium

[3] Ghent Univ IMEC, Dept Informat Technol, IDLab, Technol Pk 126, B-9052 Zwijnaarde, Belgium

[4] OCAS NV ArcelorMittal Global R&D Gent, Pres JF Kennedylaan 3, B-9060 Zelzate, Belgium

来源：

SCRIPTA MATERIALIA | 2021年 / 193卷

关键词：

Image analysis; Steels; Modeling; Scanning electron microscopy (SEM); CLASSIFICATION;

D O I：

10.1016/j.scriptamat.2020.10.026

中图分类号：

TB3 [工程材料学];

学科分类号：

0805 ; 080502 ;

摘要：

The promising results of deep learning in image recognition suggest a huge potential for microscopic analyses in materials science. One major challenge for its adoption in the study of materials is the limited number of images that are available to train models on. Herein, we present a methodology to create accurate image recognition models with small datasets. By explicitly taking into account the magnification and by introducing appropriate transformations, we incorporate as many insights from material science in the model as possible. This allows for a highly data-efficient training of complex deep learning models. Our results indicate that a model trained with the presented methodology is able to outperform human experts. (C) 2020 Acta Materialia Inc. Published by Elsevier Ltd. All rights reserved.

引用

收藏

页码：33 / 37

页数：5

相关论文

共 18 条

[1] Development of High Accuracy Segmentation Model for Microstructure of Steel by Deep Learning [J].

Ajioka, Fumito ;

Wang, Zhi-Lei ;

Ogawa, Toshio ;

Adachi, Yoshitaka .

ISIJ INTERNATIONAL, 2020, 60 (05) :954-959

[2] Advanced Steel Microstructural Classification by Deep Learning Methods [J].

Azimi, Seyed Majid ;

Britz, Dominik ;

Engstler, Michael ;

Fritz, Mario ;

Muecklich, Frank .

SCIENTIFIC REPORTS, 2018, 8

[3] Image driven machine learning methods for microstructure recognition [J].

Chowdhury, Aritra ;

Kautz, Elizabeth ;

Yener, Bulent ;

Lewis, Daniel .

COMPUTATIONAL MATERIALS SCIENCE, 2016, 123 :176-187

[4] Multi-column deep neural network for traffic sign classification [J].

Ciresan, Dan ;

Meier, Ueli ;

Masci, Jonathan ;

Schmidhuber, Juergen .

NEURAL NETWORKS, 2012, 32 :333-338

[5] Clinically applicable deep learning for diagnosis and referral in retinal disease [J].

De Fauw, Jeffrey ;

Ledsam, Joseph R. ;

Romera-Paredes, Bernardino ;

Nikolov, Stanislav ;

Tomasev, Nenad ;

Blackwell, Sam ;

Askham, Harry ;

Glorot, Xavier ;

O'Donoghue, Brendan ;

Visentin, Daniel ;

van den Driessche, George ;

Lakshminarayanan, Balaji ;

Meyer, Clemens ;

Mackinder, Faith ;

Bouton, Simon ;

Ayoub, Kareem ;

Chopra, Reena ;

King, Dominic ;

Karthikesalingam, Alan ;

Hughes, Cian O. ;

Raine, Rosalind ;

Hughes, Julian ;

Sim, Dawn A. ;

Egan, Catherine ;

Tufail, Adnan ;

Montgomery, Hugh ;

Hassabis, Demis ;

Rees, Geraint ;

Back, Trevor ;

Khaw, Peng T. ;

Suleyman, Mustafa ;

Cornebise, Julien ;

Keane, Pearse A. ;

Ronneberger, Olaf .

NATURE MEDICINE, 2018, 24 (09) :1342-+

[6] High Throughput Quantitative Metallography for Complex Microstructures Using Deep Learning: A Case Study in Ultrahigh Carbon Steel [J].

DeCost, Brian L. ;

Lei, Bo ;

Francis, Toby ;

Holm, Elizabeth A. .

MICROSCOPY AND MICROANALYSIS, 2019, 25 (01) :21-29

[7] Exploring the microstructure manifold: Image texture representations applied to ultrahigh carbon steel microstructures [J].

DeCost, Brian L. ;

Francis, Toby ;

Holm, Elizabeth A. .

ACTA MATERIALIA, 2017, 133 :30-40

[8] A computer vision approach for automated analysis and classification of microstructural image data [J].

DeCost, Brian L. ;

Holm, Elizabeth A. .

COMPUTATIONAL MATERIALS SCIENCE, 2015, 110 :126-133

[9] Microstructure reconstructions from 2-point statistics using phase-recovery algorithms [J].

Fullwood, David T. ;

Niezgoda, Stephen R. ;

Kalidindi, Surya R. .

ACTA MATERIALIA, 2008, 56 (05) :942-948

[10] Objective microstructure classification by support vector machine (SVM) using a combination of morphological parameters and textural features for low carbon steels [J].

Gola, Jessica ;

Webel, Johannes ;

Britz, Dominik ;

Guitar, Agustina ;

Staudt, Thorsten ;

Winter, Marc ;

Mucklich, Frank .

COMPUTATIONAL MATERIALS SCIENCE, 2019, 160 :186-196