Accessible Unlicensed Requires Authentication Published by De Gruyter July 6, 2020

Machine Learning for Microstructure Quantification of Different Material Classes

Maschinelles Lernen zur Gefügequantifizierung verschiedener Werkstoffklassen
A. Kumar Choudhary, A. Jansche, T. Bernthaler and G. Schneider
From the journal Practical Metallography

Abstract

Material characterization is one of the major challenges faced in the field of materials research. The general approach is the assessment of quantitative properties, which are dependent on the utilization of destructive/non-destructive techniques. Conventional methods require the user to manually assess the obtained micrographs to identify the microstructural patterns followed by physical tests to quantify properties and characterization.

A recent development in this area is the use of the concept of machine learning (ML) in image segmentation and analysis. Over the years, research in this area has resulted in the development of stable, robust and reliable systems, which yield consistently good results. This paper is aimed at introducing the use of one such machine learning approach based on Artificial Neural Networks (ANN) for image segmentation and quantification of material properties and discussion of some use cases. The results of the ML based method are compared with the results obtained from the traditional threshold based segmentation method.

Kurzfassung

Die Werkstoffcharakterisierung gehört zu den großen Herausforderungen im Bereich der Materialforschung. Der allgemeine Ansatz besteht in der Beurteilung quantitativer Eigenschaften, die von der Nutzung zerstörender bzw. zerstörungsfreier Verfahren abhängig ist. Bei konventionellen Methoden ist eine Beurteilung der erhaltenen Schliffbilder durch den Nutzer erforderlich, um Gefügemuster zu identifizieren und anschließend physikalische Tests zur Quantifizierung der Eigenschaften und zur Charakterisierung durchzuführen.

Zu den aktuellen Entwicklungen auf diesem Gebiet gehört bei der Bildsegmentierung und Bildanalyse der Einsatz von maschinellem Lernen (ML, machine learning). Die Forschung auf diesem Gebiet hat zwischenzeitlich zur Entwicklung von stabilen, robusten und zuverlässigen Systemen geführt, die beständig gute Ergebnisse liefern. Ziel dieses Beitrags ist die Vorstellung einer ML-Methode basierend auf künstlichen neuronalen Netzen (KNN) zur Bildsegmentierung und zur Quantifizierung von Werkstoffeigenschaften sowie die Diskussion einiger Anwendungsbeispiele. Die Ergebnisse der ML-basierten Methode werden mit den Ergebnissen des traditionellen Schwellenwertverfahrens verglichen.


Übersetzung: V. Müller


References / Literatur

[1] Liu, Y.; Zhao, T.; Ju, W.; Shi, S.: Materials discovery and design using machine learning, Journal of Materiomics, 3 (2017) 3, 159177 DOI: 10.1016/j.jmat.2017.08.002Search in Google Scholar

[2] Kalasova, D.; Masek, J.; Zikmund, T.; Spurny, P.; Halodaa, Y.; Burget, R.; Kaiser, J.: Segmentation of multi-phase object applying trainable segmentation, in: Proc. 7th Conf. on Industrial Computed Tomography, Belgium, 2017Search in Google Scholar

[3] Satish, S.; Anish, T.; Sureh, P.; Arunsankar, V.; Subramani, N.: Microstructure Analysis of Cast Iron using Mathematical Morphology, Int. Journal of Innovative Research in Science, Engineering and Technology, 6 (2017) 1, 23198753Search in Google Scholar

[4] Swarup, C.; Rühaak, W.; Khan, F.; Enzmann, F.; Mielke, P.; Kersten, M.; Sass, I.: Processing of rock core microtomography images: using seven different machine learning algorithms, Computer & Geosciences, 86 (2016), 120128 DOI: 10.1016/j.cageo.2015.10.013Search in Google Scholar

[5] Albuquerque, V.; Silva, C.; Menezes, S.; Farias, J.; Tavares, J.: Automatic Evaluation of Nickel Alloy Secondary Phases from SEM Images, Microscopy Research and Technique, 74 (2011) 1, 3646 DOI: 10.1002/jemt.20870Search in Google Scholar

[6] Castleman, K.: Digital Image Processing, Prentice Hall, Englewood Cliffs, USA, 1996Search in Google Scholar

[7] Saleh, S.; Kalyankar, N.V.; Khamitkar, S.: Image segmentation by using edge detection, Int. Journal on Computer Science and Engineering, 2 (2010) 3, 804807Search in Google Scholar

[8] Khokher, M.R.; Ghafoor, A.; Siddiqui, A.M.: Image segmentation using multilevel graph cuts and graph development using fuzzy rule-based system, IET Image Processing, 7 (2013) 3, 201211 DOI: 10.1049/iet-ipr.2012.0082Search in Google Scholar

[9] Angelina, S.; Suresh, L.; Veni, S.H.: Image Segmentation Based On Genetic Algorithm for Region Growth and Region Merging, in: Proc. Int. Conf. on Computing, Electronics and Electrical Technologies, India, 2012 DOI: 10.1109/ICCEET.2012.6203833Search in Google Scholar

[10] Salem, S.; Kalyankar, N.V.; Khamitkar, S.D.: Image Segmentation by Using Threshold Techniques, Journal of Computing, 2 (2010) 5, 21519617Search in Google Scholar

[11] Sarkar, D.; Bali, R.; Sharma, T.: Practical Machine Learning with Python, Apress, Berkeley, CA, 2018 DOI: 10.1007/978-1-4842-3207-1Search in Google Scholar

[12] Pavlidis, T.: Algorithms for Graphics and Image Processing, 1 edition, Springer-Verlag Berlin Heidelberg, Germany, 1982 DOI: 10.1007/978-3-642-93208-3_1Search in Google Scholar

[13] Jansche, A.; Trier, F.; Kopp, A.; Schirle, P.; Bernthaler, T.; Klauck, U.; Schneider, G.: Maschinelles Lernen zur Quantifizierung und Defekterkennung an lichtmikroskopischen Bildern prismatischer Li-Ionen Zellen, in: Tagungsband 22 Workshop Frabbildverarbeitung, Ilmenau, 2016Search in Google Scholar

[14] Albuquerque, V.; Cortez, P.; Alexandria, A.; Tavares, J.: A New Solution for Automatic Microstructures Analysis from Images Based on a Backpropagation Artificial Neural Network, Nondestructive Testing and Evaluation, 23 (2008) 4, 273283 DOI: 10.1080/10589750802258986Search in Google Scholar

[15] Albuquerque, V.; Filho, R.; Cavalcante, T.S.; Tavares, J.: New computational solution to quantify synthetic material porosity from optical microscopic images, Journal of Microscopy, 240 (2010) 1, 5059 DOI: 10.1111/j.1365-2818.2010.03384.xSearch in Google Scholar

[16] Papa, J.; Pereira, C.R.; Albuquerque, V.; SilvaC.C.; Falcäo, A.; Tavares, J.: Precipitates segmentation from scanning electron microscope images through machine learning techniques, in: Proc. 14th Int. Conf. on Combinatorial image analysis, Spain, 2011 DOI: 10.1007/978-3-642-21073-0_40Search in Google Scholar

[17] Malik, A.; Saavedra, J.T.; Fernändez, M.; Naya, S.: Classification of wood micrographs by image segmentation, Chemometrics and Intelligent Laboratory Systems, 107 (2011) 2, 351362 DOI: 10.1016/j.chemolab.2011.05.005Search in Google Scholar

[18] Nattkemper, T.W.; Wersing, H.; Schubert, W.; Ritter, H.: A neural network architecture for automatic segmentation of fluorescence micrographs, Neurocomputing, 48 (2002) 14, 357367 DOI: 10.1016/S0925-2312(01)00642-7Search in Google Scholar

[19] Suresh, L.; Shunmuganathan, K.L.; Veni, S.H.: Dermoscopic Image Segmentation using Machine Learning Algorithm, American Journal of Applied Sciences, 8 (2011) 11, 11591168 DOI: 10.3844/ajassp.2011.1159.1168Search in Google Scholar

[20] Papa, J.; Albuquerque, V.; Falcäo, A.; Tavares, J.: Fast automatic microstructural segmentation of ferrous alloy samples using optimum-path forest, in: Proc. 2nd Int. Conf. on Computational Modeling of Objects Represented in Images, New York, 2010 DOI: 10.1007/978-3-642-12712-0_19Search in Google Scholar

[21] Banerjee, S.; Ghosh, S.; Datta, S.; Saha, S.: Segmentation of dual phase steel micrograph: An automated approach, Measurement, 46 (2013) 8, 24352440 DOI: 10.1016/j.measurement.2013.04.057Search in Google Scholar

[22] Albuquerque, V.; Tavares, J.; Durão, L.M.P.: Evaluation of Delamination Damage on Composite Plates using an Artificial Neural Network for the Radiographic Image Analysis, Journal of Composite Materials, 44 (2010) 9, 11391159 DOI: 10.1177/0021998309351244Search in Google Scholar

[23] Impoco, G.; Tuminello, L.: Incremental learning to segment micrographs, Computer Vision and Image Understanding, 140 (2015), 144152 DOI: 10.1016/j.cviu.2015.03.007Search in Google Scholar

[24] Banerjee, S.; Ghosh, S.; Datta, S.; Paul, S.B.; Saha, S.: Segmentation of three phase micrograph – An automated approach, in: Proc. CUBE Int. Information Technology Conf., India, 2012 DOI: 10.1145/2381716.2381718Search in Google Scholar

[25] Jain, V.; Seung, H.S.; Turaga, S.C.: Machines that learn to segment images: a crucial technology for connectomics, Current Opinion in Neurobiology, 20 (2010) 5, 653666 DOI: 10.1016/j.conb.2010.07.004Search in Google Scholar

[26] Amza, C.: A review on neural network-based image segmentation techniques, UK, 2000Search in Google Scholar

[27] Otsu, N.: A Threshold Selection Method from Gray-Level Histograms, IEEE Transactions on Systems, Man, and Cybernetics, 09 (1979) 1, 6266 DOI: 10.1109/TSMC.1979.4310076Search in Google Scholar

[28] Jahn, A.; Thieme, L.: DGM-Ringversuch Reproduzierbare Mikroskopie – Ringversuch Mess2, Deutsche Gesellschaft für Materialkunde (DGM), 2017Search in Google Scholar

[29] Jansche, A.; Choudhary, A.K.; Badmos, O.; Baumgartl, H.; Bernthaler, T.; Büttner, R.; Schneider, G.: Künstliche Intelligenz in der Materialmikroskopie, Jahresmagazin Ingenieurwissenschaften / Werkstofftechnik 2019, 2019, 1417Search in Google Scholar

[30] Samarasinghe, S.: Neural Networks for Applied Sciences and Engineering: From Fundamentals to Complex Pattern Recognition, 1 edition, Auerbach Publications, USA, 2006Search in Google Scholar

[31] Maas, A.L.; Hannun, A.; AndrewY.N.: Rectifier nonlinearities improve neural network acoustic models, in: Proc. Int. Conf. on machine learning Workshop on Deep Learning for Audio, Speech and Language Processing, Georgia, 2013Search in Google Scholar

[32] Pedregosa, F.; Varoquaux, G.; Gramfort, A.; Michel, V.; Thirion, B.; Grisel, O.; Blondel, M.; Prettenhofer, P.; Weiss, R.; Dubourg, V.; Vanderplas, J.; Passos, A.; Cournapeau, D.; Brucher, M.; Perrot, M.: Scikit-learn: Machine Learning in Python, Journal of Machine Learning Research, 12 (2011), 28252830Search in Google Scholar

[33] Buades, A.; Coll, B.; Morel, J.: Non-Local Means Denoising, in: Proc. IEEE Computer Society Conf. on Computer Vision and Pattern Recognition, USA, 2005Search in Google Scholar

[34] Bradley, D.; Roth, G.: Adaptive Thresholding using the Integral Image, Journal of Graphics Tools, 12 (2007) 2, 1321 DOI: 10.1080/2151237X.2007.10129236Search in Google Scholar

[35] Yang, X.; Shen, X.; Long, J.; Chen, H.: An Improved Median-based Otsu Image Thresholding Algorithm, in: Proc. AASRI Conf. on Modelling, Identification and Control, 2012 DOI: 10.1016/j.aasri.2012.11.074Search in Google Scholar

[36] Klein, S.; Staring, M.; Murphy, K.; Viergever, M.A.; Pluim, J.P.W.: elastix: a toolbox for intensity based medical image registration, IEEE Transactions on Medical Imaging, 29 (2010) 1, 196205 DOI: 10.1109/TMI.2009.2035616Search in Google Scholar

Received: 2019-09-30
Accepted: 2019-12-03
Published Online: 2020-07-06
Published in Print: 2020-07-15

© 2020, Carl Hanser Verlag, München