矿业科学学报2025，Vol.10Issue(3)：408-417,10.DOI:10.19606/j.cnki.jmst.2025012
基于深度学习的稀有金属花岗岩岩性细粒度分类研究
Research on fine-grained classification of rare metal granite lithology based on deep learning
摘要
Abstract
Fine-grained image classification has high research value and application prospects in practi-cal applications.At present,the traditional lithology fine-grained classification method is highly subjec-tive and time-sensitive,depending on the experience of researcher and the quality of experimental e-quipment.Therefore,in this paper,the technology of fine-grained image classification is introduced in-to the field of granite lithology identification.The RGB image datasets of four types of lithology,namely flesh-red,grayish-white,iron-manganese,and amazonite-bearing alkali feldspar granites,are systemat-ically constructed.Comparative experiments were carried out using typical deep learning models such as AlexNet,VGG16,ResNet50 and Vision Transformer.The results show that the classification accura-cy of all models exceeds 82％,and the VGG16 model is the best,which is 88.57％,an increase of 5.71％over the AlexNet model;the amazonite-bearing alkali feldspar granite has a recognition accura-cy of 100％due to its significant characteristic minerals,while the grayish-white alkali-feldspar granite has the worst recognition effect;the model accuracy is positively correlated with the amount of training samples,and the model performance is optimal when the training set is complete.In the future,the ac-curacy of fine-grained classification of rare metal granite lithology can be further improved by improving the quantity and quality of rock samples and optimizing the model algorithm.关键词
稀有金属花岗岩/岩性分类/细粒度分类/深度学习/RGB图像Key words
rare metal granite/lithology classification/fine-grained classification/deep learning/RGB image分类
矿山工程引用本文复制引用
赵恒谦,王盼,刘志国,苗群峰,李智斌,唐广龙,齐云飞,谢雨,王蒙萌..基于深度学习的稀有金属花岗岩岩性细粒度分类研究[J].矿业科学学报,2025,10(3):408-417,10.基金项目
国家自然科学基金(41701488) （41701488）
精细勘探与国家重点实验室煤炭资源智能开发重点实验室开放研究基金(SKLCRSM24KF011) （SKLCRSM24KF011）
河北省矿产资源与生态环境监测重点实验室开放基金(HBMREEM202305) （HBMREEM202305）
中国矿业大学(北京)基本科研业务费-博士研究生拔尖创新人才培育基金(BBJ2023025) （北京）
