In the field of geological exploration,accurate rock identification is crucial for resource assessment,exploration po-sitioning,and environmental protection.However,traditional rock identification methods rely on the observation and experience of geologists,which suffer from low efficiency,subjectivity,and dependence on expert knowledge.To overcome these challenges,we proposes an automatic rock classification and recognition algorithm based on Swin-Transformer.The algorithm introduces a staged attention mechanism,dividing the image into different blocks and using windowed attention to allow each block to interact only with its neighboring blocks,significantly reducing computational and memory costs.Experimental results demonstrate that compared to popular classification models such as ResNet and EfficientNet,the proposed Swin-Transformer model achieves a significant im-provement in classification efficiency and accuracy,with a Top-1 accuracy of 91.3%and a Top-5 accuracy of 98.56%.This re-search not only enhances the accuracy and efficiency of rock identification but also reduces the reliance on manual intervention by automating the process,providing robust support for geological research and engineering applications.
关键词
岩石识别/Swin-Transformer/分类识别/机器学习/地质勘探
Key words
rock identification/Swin-Transformer/classification recognition/machine learning/geological exploration
维普
万方数据