FFSwinNet: CNN-Transformer Combined Network With FFT for Shale Core SEM Image Segmentation

Semantic segmentation, as one of the important branches in the field of computer vision, has made significant progress in recent years. However, in the field of shale exploration, the use of such computer vision techniques has not been widely explored. This study aims to fill this gap by proposing a novel visual base model for shale fracture porosity. Aiming at the unique characteristics of shale electron microscope scanning images (SEM), we introduced a fast Fourier transform module (FFT) into the feature extraction network to effectively suppress the high-frequency noise during the imaging process. By collecting and annotating 91 SEM scan images of voids and cracks in marine shale and marine-continental transitional shale, and conducting comparative experiments between our proposed model and seven classical semantic segmentation models, the results show that our method exhibits obvious advantages in both visual and quantitative metrics(4.99%, 4.35% and 5.46% improvements on the marine shale SEM image dataset and 1.90%, 0.96%, 4.81% improvements on the marine-continental transitional shale SEM image dataset). Notably, our method not only performs well in processing raw images but also maintains high segmentation accuracy after random Gaussian noise and pixel loss processing. This feature provides a new technical approach and solution in the field of shale exploration. In summary, this study has made impressive progress by combining advanced computer vision technology with the field of shale exploration. Our work not only provides an efficient and accurate image segmentation method for shale exploration but also brings useful insights and guidance for research and practice in related fields.