A froth velocity measurement method based on improved U-Net++ semantic segmentation in flotation process

Abstract

During flotation, the features of the froth image are highly correlated with the concentrate grade and the corresponding working conditions. The static features such as color and size of the bubbles and the dynamic features such as velocity have obvious differences between different working conditions. The extraction of these features is typically relied on the outcomes of image segmentation at the froth edge, making the segmentation of froth image the basis for studying its visual information. Meanwhile, the absence of scientifically reliable training data with label and the necessity to manually construct dataset and label make the study difficult in the mineral flotation. To solve this problem, this paper constructs a tungsten concentrate froth image dataset, and proposes a data augmentation network based on Conditional Generative Adversarial Nets (cGAN) and a U-Net++-based edge segmentation network. The performance of this algorithm is also evaluated and contrasted with other algorithms in this paper. On the results of semantic segmentation, a phase-correlation-based velocity extraction method is finally suggested.

Keywords

froth flotation / froth segmentation / froth image / data augmentation / velocity extraction / image features

References

[1] Lu YL, Liu DW, Jia XD, Yuan JJ, Shi DY. A review on flotation process of scheelite. Adv. Mater. Res., 2014, 962–965, 388.

[2] Chang ZY, Niu SS, Shen ZC, Zou LC, Wang HJ. Latest advances and progress in the microbubble flotation of fine minerals: Microbubble preparation, equipment, and applications. Int. J. Miner. Metall. Mater., 2023, 30(7): 1244.

[3] Moolman DW, Aldrich C, Deventer JSJ, Stange WW. Digital image processing as a tool for on-line monitoring of froth in flotation plants. Miner. Eng., 1994, 7(9): 1149.

[4] Moolman DW, Eksteen JJ, Aldrich C, van Deventer JSJ. The significance of flotation froth appearance for machine vision control. Int. J. Miner. Process., 1996, 48(3–4): 135.

[5] Moolman DW, Aldrich C, Van Deventer JSJ, Bradshaw DJ. The interpretation of flotation froth surfaces by using digital image analysis and neural networks. Chem. Eng. Sci., 1995, 50(22): 3501.

[6] Wang W, Bergholm F, Yang B. Froth delineation based on image classification. Miner. Eng., 2003, 16(11): 1183.

[7] W.X. Wang and O. Stephansson, A robust bubble delineation algorithm for froth images, [in] Proceedings of the Second International Conference on Intelligent Processing and Manufacturing of Materials. IPMM’99, Honolulu, 2002, p. 471.

[8] Jahedsaravani A, Massinaei M, Marhaban MH. An image segmentation algorithm for measurement of flotation froth bubble size distributions. Measurement, 2017, 111, 29.

[9] Zhang J, Tang ZH, Ai MX, Gui WH. Nonlinear modeling of the relationship between reagent dosage and flotation froth surface image by Hammerstein-Wiener model. Miner. Eng., 2018, 120, 19.

[10] Hargrave JM, Hall ST. Diagnosis of concentrate grade and mass flowrate in tin flotation from colour and surface texture analysis. Miner. Eng., 1997, 10(6): 613.

[11] Marais C, Aldrich C. Estimation of platinum flotation grades from froth image data. Miner. Eng., 2011, 24(5): 433.

[12] Popli K, Afacan A, Liu Q, Prasad V. Development of online soft sensors and dynamic fundamental model-based process monitoring for complex sulfide ore flotation. Miner. Eng., 2018, 124, 10.

[13] J. Zhang, Z.H. Tang, Y.F. Xie, M.X. Ai, and W.H. Gui, Convolutional memory network-based flotation performance monitoring, Miner. Eng., 151(2020), art. No. 106332.

[14] Lecun Y, Bottou L, Bengio Y, Haffner P. Gradient-based learning applied to document recognition. Proc. IEEE, 1998, 86(11): 2278.

[15] Krizhevsky A, Sutskever I, Hinton GE. ImageNet classification with deep convolutional neural networks. Commun. ACM, 2017, 60(6): 84.

[16] K. Simonyan and A. Zisserman, Very deep convolutional networks for large-scale image recognition, [in] International Conference on Learning Representations, San Diego, 2015.

[17] K.M. He, X.Y. Zhang, S.Q. Ren, and J. Sun, Deep residual learning for image recognition, [in] 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, 2016, p. 770.

[18] H. Noh, S. Hong, and B. Han, Learning deconvolution network for semantic segmentation, [in] 2015 IEEE International Conference on Computer Vision (ICCV), Santiago, 2015, p. 1520.

[19] Baxt WG. Use of an artificial neural network for the diagnosis of myocardial infarction. Ann. Intern. Med., 1991, 115(11): 843.

[20] R. Girshick, J. Donahue, T. Darrell, and J. Malik, Rich feature hierarchies for accurate object detection and semantic segmentation, [in] 2014 IEEE Conference on Computer Vision and Pattern Recognition, Columbus, 2014, p. 580.

[21] Forsyth D. Object detection with discriminatively trained part-based models. Computer, 2014, 47(2): 6.

[22] J. Wang, Y. Yang, J.H. Mao, Z.H. Huang, C. Huang, and W. Xu, CNN-RNN: A unified framework for multi-label image classification, [in] 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, 2016, p. 2285.

[23] A. Garcia-Garcia, S. Orts-Escolano, S.O. Oprea, V. Villena-Martinez, and J. Garcia-Rodriguez, A review on deep learning techniques applied to semantic segmentation, 2017. https://arxiv.org/abs/1704.06857v1.

[24] J. Long, E. Shelhamer, and T. Darrell, Fully convolutional networks for semantic segmentation, [in] 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, 2015, p. 3431.

[25] Chen LC, Papandreou G, Kokkinos I, Murphy K, Yuille AL. DeepLab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. IEEE Trans. Pattern Anal. Mach. Intell., 2018, 40(4): 834.

[26] Liu JP, Gao QQ, Tang ZH, et al. Online monitoring of flotation froth bubble-size distributions via multiscale deblurring and multistage jumping feature-fused full convolutional networks. IEEE Trans. Instrum. Meas., 2020, 69(12): 9618.

[27] B.K. Gharehchobogh, Z.D. Kuzekanani, J. Sobhi, and A.M. Khiavi, Flotation froth image segmentation using Mask R-CNN, Miner. Eng., 192(2023), art. No. 107959.

[28] O. Ronneberger, P. Fischer, and T. Brox, U-Net: Convolutional networks for biomedical image segmentation, [in] N. Navab, J. Hornegger, W.M. Wells, and AF. Frangi, eds., Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015, Part III, Munich, 2015, p. 234.

[29] Z.W. Zhou, M.M.R. Siddiquee, N. Tajbakhsh, and J.M. Liang, UNet++: A nested U-Net architecture for medical image segmentation, [in] D. Stoyanov, Z. Taylor, G. Carneiro, et al., eds., Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support (DLMIA 2018, ML-CDS 2018), Granada, 2018, p. 3.

[30] Dosovitskiy A, Fischer P, Springenberg JT, Riedmiller M, Brox T. Discriminative unsupervised feature learning with exemplar convolutional neural networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016, 38(9): 1734.

[31] Jiang ZX, Zhang H, Wang Y, Ko SB. Retinal blood vessel segmentation using fully convolutional network with transfer learning. Comput. Med. Imag. Graph., 2018, 68, 1.

[32] Goodfellow IJ, Pouget-Abadie J, Mirza M, et al. Generative adversarial networks. Commun. ACM, 2020, 63(11): 139.

[33] X. Yi, E. Walia, and P. Babyn, Generative adversarial network in medical imaging: A review, Med. Image Anal., 58(2019), art. No. 101552.

[34] M. Mirza and S. Osindero, Conditional generative adversarial nets, 2014. https://arxiv.org/abs/1411.1784

[35] A. Radford, L. Metz, and S. Chintala, Unsupervised representation learning with deep convolutional generative adversarial networks, 2015. https://arxiv.org/abs/1511.06434

[36] C. Szegedy, W. Liu, Y.Q. Jia, et al., Going deeper with convolutions, [in] 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, 2015, p. 1.

[37] Srivastava N, Hinton G, Krizhevsky A, Sutskever I, Salakhutdinov R. Dropout: A simple way to prevent neural networks from overfitting. J. Mach. Learn. Res., 2014, 15(1): 1929.

[38] A. Painsky and G. Wornell, On the universality of the logistic loss function, [in] 2018 IEEE International Symposium on Information Theory (ISIT), Vail, 2018, p. 936.

[39] P. Ramachandran, B. Zoph, and Q.V. Le, Searching for activation functions, 2017. http://arxiv.org/abs/1710.05941

[40] Hargrave JM, Miles NJ, Hall ST. The use of grey level measurement in predicting coal flotation performance. Miner. Eng., 1996, 9(6): 667.

[41] Jahedsaravani A, Marhaban MH, Massinaei M. Prediction of the metallurgical performances of a batch flotation system by image analysis and neural networks. Miner. Eng., 2014, 69, 137.

[42] Massinaei M, Jahedsaravani A, Taheri E, Khalilpour J. Machine vision based monitoring and analysis of a coal column flotation circuit. Powder Technol., 2019, 343, 330.

[43] Zhou YL, Li HW. The analysis of gas-liquid two-phase flow patterns based on variation coefficient of image connected regions and line-correlation algorithm. Energy Procedia, 2012, 17, 933.