Gas-liquid two-phase flow is widely involved in many scientific and technological fields, such as energy, electricity, nuclear energy, aerospace and environmental protection. In some fields, extracting the accurate position of bubbles in space can not only accurately capture the characteristics of bubbles in two-phase flow, but also plays an important role in the subsequent research like bubble tracking. It has got some progresses to use Convolutional Neural Network (CNNs) to identify bubbles in gas-liquid two-phase flow, while accurate pixel segmentation map in the bubble identification problem is more desirable in many areas. In this paper, VGG16-FCN model and U-Net model are utilized to identify bubbles in two-phase flow images from the perspective of semantic segmentation. LabelMe is used to label the images in the experiment, which can remove the noise in the original image. In addition, bubble pixels with low ratio relative to the background affects the loss function value tinily which cause the irrational evaluation for the recognition in traditional semantic segmentation, thus, Dice loss is used as the loss function for training to improve the recognition effect. The research results show that the two deep learning models have strong feature extraction ability and accurately detect the bubble boundary.

[1] Acuña C. and Finch J., “Tracking Velocity of Multiple Bubbles in A Swarm,” International Journal of Mineral Processing, vol. 94, no. 3-4, pp. 147-158, 2010. https://doi.org/10.1016/j.minpro.2010.02.001

[2] Akhmetbekov Y., Alekseenko S., and Dulin V., “Planar Fluorescence for Round Bubble Imaging And its Application for the Study of an Axisymmetric Two-Phase Jet,” Experiments in Fluids, vol. 48, no. 4, pp. 615-629, 2010. https://doi.org/10.1007/s00348-009-0797-0

[3] Asher W., Karle L., and Higgins B., “The Influence of Bubble Plumes on Air Seawater Gas Transfer Velocities,” Journal of Geophysical Research, vol. 101, no. C5, pp. 12027-12041, 1996. https://doi.org/10.1029/96JC00121

[4] Asselin C., Comeau Y., and Ton-That Q., “Alpha Correction Factors for Static Aerators and Fine Bubble Diffusers Used in Municipal Facultative Aerated Lagoons,” Water Science and Technology,vol. 38, no. 3, pp. 79-85, 1998. https://doi.org/10.1016/S0273-1223(98)00555-1

[5] Audebert N., Saux B., and Lefèvre S., “Semantic Segmentation of Earth Observation Data Using Multimodal and Multi-scale Deep Networks,” in Proceeding of Asian Conference on Computer Vision, pp. 180-196, 2016. https://doi.org/10.48550/arXiv.1609.06846

[6] Badrinarayanan V., Kendall A., and Cipolla R., “SegNet: A Deep Convolutional Encoder Decoder Architecture for Scene Segmentation,” IEEE Trans Pattern Anal Mach Intell, vol. 39, no. 12, pp. 2481-2495, 2017. DOI: 10.1109/TPAMI.2016.2644615

[7] Cerqueira R., Paladino E., Ynumaru B., and Maliska C., “Image Processing Techniques for the Measurement of Two-Phase Bubbly Pipe Flows using Particle Image and Tracking Velocimetry (PIV/PTV),” Chemical Engineering Science, vol. 189, pp. 1-23, 2018. https://doi.org/10.1016/j.ces.2018.05.029

[8] Cerqueira R. and Paladino E., “Development of A Deep Learning-Based Image Processing Technique for Bubble Pattern Recognition and Shape Reconstructionin Dense Bubbly Flows,” Chemical Engineering Science, vol. 230, pp. 116163, 2021. https://doi.org/10.1016/j.ces.2020.116163

[9] Chen G., Li C., Wei W., and Jing W., “Fully Convolutional Neural Network with Augmented Atrous Spatial Pyramid Pool and Fully Connected Fusion Path for High Resolution Remote Sensing lmage Segmentation,” Applied Sciences, vol. 9, no. 9, pp. 1-14, 2019. https://doi.org/10.3390/app9091816

[10] Chen L., Papandreou G., Kokkinos I., Murphy K., and Yuille A., “DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs,” IEEE Transactions on Pattern Analysis and Machine Intelligence , vol. 40, no. 4, pp. 834-848, 2016. DOI: 10.1109/TPAMI.2017.2699184

[11] Chen L., Papandreou G., Schroff F., and Hartwig A., “Rethinking Atrous Convolution for Semantic Image Segmentation,” arXiv preprint, 2017. 10.48550/arXiv.1706.05587

[12] Clift R., Grace J., and Weber M., Bubbles, Drops, and Particles, Courier Corporation, 1978. https://doi.org/10.1016/j.cej.2022.137859

[13] Cui Y., Li C., Zhang W., Ning X., Shi X., Gao J., 616 The International Arab Journal of Information Technology, Vol. 20, No. 4, July 2023 and Lan X., “A Deep Learning-Based Image Processing Method for Bubble Detection, Segmentation, and Shape Reconstruction in High Gas Holdup Sub-Millimeter Bubbly Flows,” Chemical Engineering Journal, vol. 449, pp. 137859, 2022. https://doi.org/10.1016/j.cej.2022.137859

[14] Dalal N. and Triggs B., “Histograms of Oriented Gradients for Human Detection,” in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Diego, pp. 886-893, 2005. DOI: 10.1109/CVPR.2005.177

[15] Dulin V., Markovich D., and Pervunin K., “The Optical Principles of PFBI Approach,” AIP Conference Proceedings, vol. 1428, pp. 1, 2012. https://doi.org/10.1063/1.3694709

[16] Elumalai G., and Ganesan M., “Deep Learning Based Hand Wrist Segmentation using Mask R- CNN,” The International Arab Journal of Information Technology, vol. 19, no.5, pp. 785- 792, 2022. https://iajit.org/portal/images/Year2022/No.5/198 43.pdf

[17] Farmer D., McNeil C., and Johnson B., “Evidence for the Importance of Bubbles in Increasing Air- Sea Gas Flux,” Nature, vol. 361, no. 18, pp. 620- 623, 1993. 10.1038/361620a0

[18] Fu G., Liu C., Zhou R., Sun T., and Zhang Q., “Classification for High Resolution Remote Sensing Imagery Using a Fully Convolutional Network,” Remote Sens, vol. 9, no. 5, pp. 498, 2017. https://doi.org/10.3390/rs9050498

[19] Garnier C., Lance M., and Marié J., “Measurement of Local Flow Characteristics in Buoyancy Driven Bubbly Flow At High Void Fraction,” Experimental Thermal and Fluid Science, vol. 26, no. 6-7, pp. 811-815, 2002. https://doi.org/10.1016/S0894-1777(02)00198-X

[20] Guo Z., Shao X., Xu Y., Miyazaki H., Ohira W., and Shibasaki R., “Identification of Village Building via Google Earth Images and Supervised Machine Learning Methods,” Remote Sens, vol. 8, no. 4, pp. 271, 2016. https://doi.org/10.3390/rs8040271

[21] Haas T., Schubert C., Eickhoff M., and Pfeifer H., “Bubcnn: Bubble Detection Using Faster RCNN and Shape Regression Network,” Chemical Engineering Science, vol. 216, pp. 115467, 2020. https://doi.org/10.1016/j.ces.2019.115467

[22] Karn A., Ellis C., Arndt R., and Hong J., “An Integrative Image Measurement Technique for Dense Bubbly Flows with A Wide Size Distribution,” Chemical Engineering Science, vol. 122, pp. 240-249, 2015. https://doi.org/10.1016/j.ces.2014.09.036

[23] Kawase Y., Halard B., and Moo-Young M., “Liquid Phase Mass Transfer Coefficients in Bioreactors,” Biotechnology and Bioengineering, vol. 39, no. 11, pp. 1133-1140, 1992. DOI: 10.1002/bit.260391109

[24] Kim S., Fu X., Wang X., and Ishii M., “Development of the Miniaturized Four-Sensor Conductivity Probe and The Signal Processing Scheme,” International Journal of Heat and Mass Transfer, vol. 43, no. 22, pp. 4101-4118, 2000. https://doi.org/10.1016/S0017-9310(00)00046-6

[25] Kulikajevas A., Maskeliūnas R., Damaševičius R., and Misra S., “Reconstruction of 3D Object Shape Using Hybrid Modular Neural Network Architecture Trained on 3D Models from ShapeNetCore Dataset,” Sensors(Basel), vol. 19, no. 7, pp. 1553, 2019. 10.3390/s19071553

[26] Lau Y., Deen N., and Kuipers J., “Development of an Image Measurement Technique for Size Distribution in Dense Bubbly Flows,” Chemical Engineering Science, vol. 94, pp. 20-29, 2013. https://doi.org/10.1016/j.ces.2013.02.043

[27] Li R., Liu W., Yang L., Sun S., Hu W., Zhang F., and Li W., “Deepunet: A Deep Fully Convolutional Network for Pixel-Level Sea-Land Segmentation,” IEEE J Sel Top Appl Earth Observ Remote Sens, vol. 11, no. 11, pp. 3954-3962, 2018. DOI: 10.1109/JSTARS.2018.2833382

[28] Li Y., Xu L., Rao J., Guo L., Yan Z., and Jin S., “A Y-Net Deep Learning Method for Road Segmentation Using High-Resolution Visible Remote Sensing Images,” Remote Sensing Letters, vol. 10, no. 4, pp. 381-390, 2019. https://doi.org/10.1080/2150704X.2018.1557791

[29] Liu Z., Qi F., Li B., and Cheung S., “Modeling of Bubble Behaviors And Size Distribution in A Slab Continuous Casting Mold,” International Journal of Multiphase Flow, vol. 79, pp. 190- 201, 2016. https://doi.org/10.1016/j.ijmultiphaseflow.2015.0 7.009

[30] Lowe D., “Distinctive Image Features from Scale- Invariant Keypoints,” International Journal of Computer Vision, vol. 60, pp. 91-110, 2004. https://doi.org/10.1023/B:VISI.0000029664.9961 5.94

[31] Maggiori E., Tarabalka Y., Charpiat G., and Alliez P., “Convolutional Neural Networks for Large- Scale Remote Sensing Image Classification,” IEEE Transactions on Geoscience and Remote Sensing, vol. 55, pp. 645-657, 2016. DOI: 10.1109/TGRS.2016.2612821

[32] Mboga N., Georganos S., Grippa T., Lennert M., Vanhuysse S., and Wolff E., “Fully Convolutional Networks and Geographic Object-Based Image Analysis for the Classification of VHR Imagery,” Remote Sensing, vol. 11, no. 5, pp. 597, 2019. 10.3390/rs11050597

[33] Poletaev I., Tokarev M., and Pervunin K., “Bubble Patterns Recognition using Neural Networks: Application to The Analysis of A Two-Phase Intelligent Recognition of Gas-Liquid Two-Phase Flow Based on Optical Image 617 Bubbly Jet,” International Journal of Multiphase Flow, vol. 126, pp. 103194, 2020. https://doi.org/10.1016/j.ijmultiphaseflow.2019.1 03194

[34] Ronneberger O., Fischer P., and Brox T., “U-Net: Convolutional Networks for Biomedical Image Segmentation,” in Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Munich, pp. 234-241, 2015.

[35] Shelhamer E., Long J., and Darrell T., “Fully Convolutional Networks for Semantic Segmentation,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 39, pp. 640-651, 2017. DOI: 10.1109/TPAMI.2016.2572683

[36] Simonnet M., Gentric C., Olmos E., and Midoux N., “Experimental Determination of the Drag Coefficient in A Swarm of Bubbles,” Chemical Engineering Science, vol. 62, pp. 858-866, 2007. https://doi.org/10.1016/j.ces.2006.10.012

[37] Szegedy C., Toshev A., and Erhan D., “Deep Neural Networks for Object Detection,” Advances in Neural Information Processing Systems and Curran Associates Inc, vol. 26, pp. 2553-2561, 2013.

[38] Wen D., Chen W., Yin J., Song Y., Ren M., and Wang D., “Overlapping Bubble Detection and Tracking Method Based on Convolutional Neural Network and Kalman Filter,” Chemical Engineering Science, vol. 263, pp. 118059, 2022. https://doi.org/10.1016/j.ces.2022.118059

[39] Woolf D., Bubbles and Their Role in Gas Exchange, Cambridge: Cambridge University Press, 1997.

[40] Yuan J., “Automatic Building Extraction in Aerial Scenes Using Convolutional Networks,” arXiv preprint, 2016. https://doi.org/10.48550/arXiv.1602.06564