Pore extraction method of rock thin section based on Attention U-Net

Abstract

Abstract This paper proposes a solution to the shortcomings of traditional segmentation methods. The labeling method uses the incomplete labeling method in weakly supervised labeling to simplify labeling and combines transfer learning to initialize the weight of the network in advance. According to the above ideas, an end-to-end deep learning model is trained. The fine rock particles have a greater segmentation impact, and in addition to that, when compared with the popular deep learning semantic segmentation approaches, they also have a significant improvement. The next phase is to continue improving the network by optimizing the parameters, with the number of network layers and the total number of parameters remaining unaltered. This requirement must be satisfied before moving on to the next stage. The capability of generalization enhances the impact of segmentation on particles as well as their accuracy. Experiments show that this method is significantly better than the traditional method for segmenting rock flakes with manual operation and has better results in the segmentation and extraction of fine particles compared with the mainstream convolutional neural network.