Hostname: page-component-76fb5796d-9pm4c Total loading time: 0 Render date: 2024-04-26T13:42:59.824Z Has data issue: false hasContentIssue false
  • English
  • Français

Material Image Segmentation with the Machine Learning Method and Complex Network Method

Published online by Cambridge University Press:  14 January 2019

Chuanbin Lai ,
Leilei Song ,
Yuexing Han ,
Qian Li ,
Hui Gu ,
Bing Wang ,
Quan Qian  and
Wei Chen
Chuanbin Lai
Affiliation:
School of Computer Engineering and Science, Shanghai University, 99 Shangda Road, Shanghai, CHINA, 200444;
Leilei Song
Affiliation:
School of Computer Engineering and Science, Shanghai University, 99 Shangda Road, Shanghai, CHINA, 200444;
Yuexing Han*
Affiliation:
School of Computer Engineering and Science, Shanghai University, 99 Shangda Road, Shanghai, CHINA, 200444; Shanghai Institute for Advanced Communication and Data Science, Shanghai University, 99 Shangda Road, Shanghai, CHINA, 200444;
Qian Li
Affiliation:
Material Genome Institute & School of Materials Science and Engineering , Shanghai University , 99 Shangda Road, Shanghai, CHINA, 200444;
Hui Gu
Affiliation:
Material Genome Institute & School of Materials Science and Engineering , Shanghai University , 99 Shangda Road, Shanghai, CHINA, 200444;
Bing Wang
Affiliation:
School of Computer Engineering and Science, Shanghai University, 99 Shangda Road, Shanghai, CHINA, 200444;
Quan Qian
Affiliation:
School of Computer Engineering and Science, Shanghai University, 99 Shangda Road, Shanghai, CHINA, 200444; Shanghai Institute for Advanced Communication and Data Science, Shanghai University, 99 Shangda Road, Shanghai, CHINA, 200444;
Wei Chen
Affiliation:
Key Laboratory of Power Beam Processing, AVIC Manufacturing Technology Institute, Beijing, CHINA, 100024;
*
*hanyuexing@gmail.com

Abstract

Core share and HTML view are not available for this content. However, as you have access to this content, a full PDF is available via the ‘Save PDF’ action button.

The study of the relationship among the manufacturing process, the structure and the property of materials can help to develop the new materials. The material images contain the microstructures of materials, therefore, the quantitative analysis for the material images is the important means to study the characteristics of material structures. Generally, the quantitative analysis for the material microstructures is based on the exact segmentation of the materials images. However, most material microstructures are shown with various shapes and complex textures in images, and they seriously hinder the exact segmentation of the component elements. In this research, machine learning method and complex networks method are adopted to the challenge of automatic material image segmentation. Two segmentation tasks are completed: on the one hand, the images of the titanium alloy are segmented based on the pixel-level classification through feature extraction and machine learning algorithm; on the other hand, the ceramic images are segmented with the complex networks theory. In the first task, texture and shape features near each pixel in titanium alloy image are calculated, such as Gabor filters, Hu moments and GLCM (Gray-Level Co-occurrence Matrix) etc.. The feature vector for the pixel can be obtained by arraying these features. Then, classification is performed with the random forest model. Once each pixel is classified, the image segmentation is completed. In the second task, a complex network structure is built for the ceramic image. Then, a clustering algorithm of complex network is used to obtain network connection area. Finally, the clustered network structure is mapped back to the image and getting the contours among the component elements. The experimental results demonstrate that these methods can accurately segment material images.

Keywords

microstructurescanning electron microscopy (SEM)optical metallographycompound
Type
Articles
Information
MRS Advances , Volume 4 , Issue 19: Broader Impact/Machine Learning and Robotics , 2019 , pp. 1119 - 1124
Copyright
Copyright © Materials Research Society 2019 

References

Chen, Y, Chen, J. A watershed segmentation algorithm based on ridge detection and rapid region merging. in: Signal Processing, Communications and Computing (ICSPCC), 2014 IEEE International Conference on, IEEE, 2014:420 424.Google Scholar
Liu, J, Chen, J. An improved iterative watershed according to ridge detection for segmentation of metallographic image. Metallographic Image, 2012:8.Google Scholar
Albuquerque, D, Victor, H C, Joa o Manuel, R S, Cortez, P C, Quantification of the microstructures of hypoeutectic white cast iron using mathematical morphology and an artificial neural network. Inter- national Journal of Microstructure and Materials Properties, 2010, 5(1):52-64.CrossRefGoogle Scholar
He, W N, Zhang, L L, Study on artificial neuronal networks applied on microstructure segmentation from metallographic images. Electronic Design Engineering, 2013, 3:49.Google Scholar
Azimi, S M, Britz, D, Engstler, M, Fritz, M, Mucklich, F. Advanced Steel Microstructural Classification by Deep Learning Methods, Scientific reports, 2018, 8(1).CrossRefGoogle ScholarPubMed
Long, J., Shelhamer, E. & Darrel, T. Fully convolutional networks for semantic segmentation. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2015).Google Scholar
Feichtinger, H G, Luef, F. Gabor Analysis and Algorithms[J]. Applied & Numerical Harmonic Analysis, 1998, 1:123-170.Google Scholar
Feichtinger, H G, Strohmer, Thomas Eds. Gabor analysis and algorithms: Theory and applications. Springer Science & Business Media, 2012.Google Scholar
Hu, M K. Visual pattern recognition by moment invariants. IRE transactions on information theory, 1962, 8(2): 179-187.Google Scholar
Dalal, N, Bill, T. Histograms of oriented gradients for human detection. Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference on, 2005:1.Google Scholar
Haralick, R M, Karthikeyan, S. Textural features for image classification. IEEE Transactions on systems, man, and cybernetics, 1973, 6: 610-621.CrossRefGoogle Scholar
Breiman, L. Random forests. Machine learning, 2001, 4(1): 5-32.CrossRefGoogle Scholar
Breiman, L, Friedman, J H, Olshen, R A, Stone, C J. Classification and regression trees. 1984.Google Scholar
Cuadros, O, Botelho, G, Rodrigues, F, Neto, JB. Segmentation of large images with complex networks. SIBGRAPI 2012: 24-31. DOI: 10.1109/SIBGRAPI.2012.13.Google Scholar
Machado, B. B., Scabini, L. F., Orue, J. P. M., de Arruda, M. S., Goncalves, D. N., Goncalves, W. N., Moreira, R., and Rodrigues-, J. F. Jr, A complex network approach for nanoparticle agglomeration analysis in nanoscale images, Journal of Nanoparticle Research, 2017, 19(2):65.CrossRefGoogle Scholar
Suzuki, S. and Abe, K: Topological structural analysis of digital binary images by border following, CVGIP, 1985, 30:32-46.Google Scholar