BubGAN: Bubble Generative Adversarial Networks for Synthesizing Realistic Bubbly Flow Images
This provides a tool for researchers in fluid dynamics to create labeled training data without manual effort, though it is incremental as it builds on existing GAN methods.
The authors tackled the problem of generating realistic synthetic bubbly flow images for training and benchmarking bubble detection algorithms, resulting in BubGAN, which can generate a million labeled bubble images with controlled properties like aspect ratio and circularity.
Bubble segmentation and size detection algorithms have been developed in recent years for their high efficiency and accuracy in measuring bubbly two-phase flows. In this work, we proposed an architecture called bubble generative adversarial networks (BubGAN) for the generation of realistic synthetic images which could be further used as training or benchmarking data for the development of advanced image processing algorithms. The BubGAN is trained initially on a labeled bubble dataset consisting of ten thousand images. By learning the distribution of these bubbles, the BubGAN can generate more realistic bubbles compared to the conventional models used in the literature. The trained BubGAN is conditioned on bubble feature parameters and has full control of bubble properties in terms of aspect ratio, rotation angle, circularity and edge ratio. A million bubble dataset is pre-generated using the trained BubGAN. One can then assemble realistic bubbly flow images using this dataset and associated image processing tool. These images contain detailed bubble information, therefore do not require additional manual labeling. This is more useful compared with the conventional GAN which generates images without labeling information. The tool could be used to provide benchmarking and training data for existing image processing algorithms and to guide the future development of bubble detecting algorithms.