Multi-axis frequency domain residual UNet for pore identification in deep shale scanning electron microscopy images

The characterization of shale pore size, surface area, porosity, fractal dimension, and other parameters is crucial for estimating shale gas reserves. Scanning electron microscope (SEM) images of shale provide comprehensive information on organic pores, inorganic pores, and micro-fractures within the rock. However, there are limited intelligent segmentation methods available for shale SEM images. To address this gap, we introduce a multi-axis frequency domain residual semantic segmentation network, referred to as MaFR2UNet. This network refines the feature extraction process within each of the four multi-scale branches of the Res2Net architecture. It incorporates a frequency-domain-leveraging multi-axis frequency domain residual block (MaFR) to enhance the network’s feature extraction capabilities. This design enables the model to effectively capture texture and detailed features within the image. Experimental results on a shale SEM image dataset demonstrate the superior segmentation performance of the refined algorithm.