Advertisement

Detection and segmentation of iron ore green pellets in images using lightweight U-net deep learning network

  • Jiaxu Duan
  • Xiaoyan LiuEmail author
  • Xin Wu
  • Chuangang Mao
Original Article
  • 27 Downloads

Abstract

In steel manufacturing industry, powdered iron ore is agglomerated in a pelletizing disk to form iron ore green pellets. The agglomeration process is usually monitored using a camera. As pellet size distribution is one of the major measures of product quality monitoring, pellets detection and segmentation from the image are the key steps to determine the pellet size. Traditional image processing algorithms are not only challenged by the complicated constitution of pellets, sediment and residuals in the image, but also by the harsh and unbalanced light reflection on the pellet centrum area and the background which results in tedious parameter adjustment work and pool performance. To solve these problems, we design a lightweight U-net deep learning network to automatically detect pellets from images and to obtain the probability maps of pellet contours. Compared to classic U-net, the proposed network has fewer parameters and introduces batch normalization layers, which greatly reduces the computing time and improves generalization ability of the network. A concentric circle model is then used to separate clumped contours of the pellets, and the pellets shapes are detected via ellipse fitting. The proposed method is verified using images captured from an industrial pelletizing disk, and its performance is compared with traditional methods and the classic U-net. Results show that the proposed method achieves better segmentation performance in DICE and ROC indexes and shows good robustness to uneven illumination. Tests on temporal image sequences demonstrate that the proposed method is effective in monitoring the pellet size distribution and the pellet shape as well. Results of this work have potential usage in online detection of iron ore green pellets and other types of particles.

Keywords

Iron ore pellets U-net deep neural network Image segmentation Particle size distribution 

Notes

Acknowledgements

Financial support from National Natural Science Foundation of China (No. 61374149) and Hunan Key Laboratory of Intelligent Robot Technology in Electronic Manufacturing (No. 2018001) is greatly appreciated.

References

  1. 1.
    e Silva BB, da Cunha ER, de Carvalho RM, Tavares LM (2018) Modeling and simulation of green iron ore pellet classification in a single deck roller screen using the discrete element method. Powder Technol 332:359–370Google Scholar
  2. 2.
    Liao CW, Tarng YS (2009) On-line automatic optical system for coarse particle size distribution. Powder Technol 189:508–513Google Scholar
  3. 3.
    Facco P, Santomaso AC, Barolo M (2017) Artificial vision system for particle size characterization from bulk materials. Chem Eng Sci 164:246–257Google Scholar
  4. 4.
    Laitinen N, Antikainen O, Yliruusi J (2002) Does a powder surface contain all necessary information for particle size distribution analysis? Eur J Pharm Sci 17:217–227Google Scholar
  5. 5.
    Sandler N (2011) Photometric imaging in particle size measurement and surface visualization. Int J Pharm 417:227–234Google Scholar
  6. 6.
    Heydari M, Amirfattahi R, Nazari B, Rahimi P (2016) An industrial image processing-based approach for estimation of iron ore green pellet size distribution. Powder Technol 303:260–268Google Scholar
  7. 7.
    Hamzeloo E, Massinaei M, Mehrshad N (2014) Estimate of particle size distribution on an industrial conveyor belt using image analysis and neural networks. Powder Technol 261:185–190Google Scholar
  8. 8.
    Thurley M (2014) Measuring the visible particles for automated online particle size distribution estimation. In: IMPC 2014, 20–24 Oct 2014, Santiago, ChileGoogle Scholar
  9. 9.
    Heydari M, Amirfattahi R, Nazari B, Rahimi P (2016) An industrial image processing-based approach for estimation of iron ore green pellet size distribution. Powder Technol 303:260–268Google Scholar
  10. 10.
    Subramanyam V, Patra P, Singh MK (2017) Automatic image processing based size characterization of green pellets. Int J Autom Smart 7(3):85–91Google Scholar
  11. 11.
    Roozbahani MM, Borela R, Frost JD (2017) Pore size distribution in granular material microstructure. Materials 10(11):1237–1257Google Scholar
  12. 12.
    Nellros F, Thurley MJ (2011) Automated image analysis of iron-ore pellet structure using optical microscopy. Miner Eng 24(14):1525–1531Google Scholar
  13. 13.
    Budzan S, Pawełczyk M (2016) Grain size determination and classification using adaptive image segmentation with shape-context information for indirect mill faults detection. In: International Congress on Technical Diagnosis, ICDT 2016, 12–16 Sept 2016, Gliwice, Poland, pp 215–224Google Scholar
  14. 14.
    Budzan S, Pawełczyk M (2018) Grain size determination and classification using adaptive image segmentation with grain shape information for milling quality evaluation. Diagnostyka 19(1):41–48Google Scholar
  15. 15.
    Lu ZM, Zhu FC, Gao XY et al (2018) In-situ particle segmentation approach based on average background modeling and graph-cut for the monitoring of l-glutamic acid crystallization. Chemom Intell Lab Syst 178:11–23Google Scholar
  16. 16.
    Zhang B, Abbas A, Romagnoli JA (2011) Multi-resolution fuzzy clustering approach for image-based particle characterization for particle systems. Chemom Intell Lab Syst 107(1):155–164Google Scholar
  17. 17.
    Chalfoun J, Majurski M, Dima A et al (2014) FogBank: a single cell segmentation across multiple cell lines and image modalities. BMC Bioinform 15:431Google Scholar
  18. 18.
    Zhang H, Ji Y, Huang W, Liu L (2018) Sitcom-star-based clothing retrieval for video advertising: a deep learning framework. Neural Comput Appl.  https://doi.org/10.1007/s00521-018-3579-x Google Scholar
  19. 19.
    Wang Y, Mao H, Yi Z (2017) Stem cell motion-tracking by using deep neural networks with multi-output. Neural Comput Appl.  https://doi.org/10.1007/s00521-017-3291-2 Google Scholar
  20. 20.
    Plissiti ME, Nikou C (2012) Overlapping cell nuclei segmentation using a spatially adaptive active physical model. IEEE Trans Image Process 21(11):4568–4580MathSciNetzbMATHGoogle Scholar
  21. 21.
    Fabijanska A (2018) Segmentation of corneal endothelium images using a U-Net-based convolutional neural network. Artif Intell Med 88:1–13Google Scholar
  22. 22.
    Park JW, Carranza A, Jiang Z (2017) Semantic segmentation of 3D particle interaction data using fully convolutional DenseNet. In: 2017 IEEE conference on computer vision and pattern recognition workshops. Honolulu, Hawaii, USA, 21–26 July 2017Google Scholar
  23. 23.
    Shahid L, Janabi-Sharifi F (2018) A neural network-based method for coverage measurement of shot-peened panels. Neural Comput Appl.  https://doi.org/10.1007/s00521-017-3339-3 Google Scholar
  24. 24.
    Ronneberger O, Fischer P, Brox T (2015) U-net: convolutional networks for biomedical image segmentation. In: Medical image computing and computer-assisted intervention (MICCAI), LNCS, vol 9351, pp 234–241Google Scholar
  25. 25.
    Ying X, Zhanyi H (2004) Catadioptric camera calibration using geometric invariants. IEEE PAMI 26(10):1260–1271Google Scholar
  26. 26.
    Fitzgibbon A, Pilu M, Fisher RB (1999) Direct least square fitting of ellipses. IEEE PAMI 21(5):476–480Google Scholar
  27. 27.
    Felzenszwalb PF, Huttenlocher DP (2004) Distance transforms of sampled functions. Theory Comput 8(19):415–428MathSciNetzbMATHGoogle Scholar
  28. 28.
    Roerdink JBTM, Meijster A (2001) The watershed transform: definitions, algorithms and parallelization strategies. Fundam Inform 41:187–228MathSciNetzbMATHGoogle Scholar
  29. 29.
    Vincent L (1990) Algorithmes Morphologiques a Base de Files d’Attente et de Lacets. Extension aux Graphes. PhD thesis, Ecole Nationale Sup´erieure des Mines de Paris, FontainebleauGoogle Scholar
  30. 30.
    Vincent L, Soille P (1991) Watersheds in digital spaces: an efficient algorithm based on immersion simulations. IEEE Trans Pattern Anal Mach Intell 13(6):583–598Google Scholar
  31. 31.
    Koomsap P, Chansri N (2014) Topological hierarchy-contour tracing algorithm for nests of interconnected contours. Int J Adv Manuf Technol 70:1247–1266Google Scholar
  32. 32.
    Liu Q, Hong X, Zou B et al (2017) Hierarchical contour closure-based holistic salient object detection. IEEE Trans Image Process 26(9):4537–4552MathSciNetGoogle Scholar
  33. 33.
    Arbeláez P, Maire M, Fowlkes C, Malik J (2011) Contour detection and hierarchical image segmentation. IEEE Trans Pattern Anal Mach Intell 33(5):898–916Google Scholar
  34. 34.
    Takashimizu Y, Iiyoshi M (2016) New parameter of roundness R: circularity corrected by aspect ratio. Prog Earth Planet Sci 3(1):1–16Google Scholar
  35. 35.
    Kaushal B, Jain K, Sharma SK (2014) Estimation of area under receiver operating characteristic curve for bi-pareto and bi-two parameter exponential models. Open J Stat 4:1–10Google Scholar
  36. 36.
    Gui N, Yang X, Jiyuan T, Jiang S (2017) Effect of roundness on the discharge flow of granular particles. Powder Technol 314:140–147Google Scholar

Copyright information

© Springer-Verlag London Ltd., part of Springer Nature 2019

Authors and Affiliations

  • Jiaxu Duan
    • 1
  • Xiaoyan Liu
    • 1
    • 2
    Email author
  • Xin Wu
    • 1
  • Chuangang Mao
    • 1
  1. 1.College of Electrical and Information EngineeringHunan UniversityChangshaChina
  2. 2.Hunan Key Laboratory of Intelligent Robot Technology in Electronic ManufacturingChangshaChina

Personalised recommendations