基于多分辨率图像的矿物特征自动提取与矿物智能识别模型  

Automatic Extraction of Mineral Features and Intelligent Classification of Minerals Based on Multi-Resolution Images

作　　者：杨彪[1,2,3] 倪瑞璞 高皓 马亦骥 曾德明 YANG Biao;NI Ruipu;GAO Hao;MA Yiji;ZENG Deming(School of Information Engineering and Automation,Kunming University of Science and Technology,Kunming,650500,China;Key Laboratory of Artificial Intelligence of Yunnan Province,Kunming University of Science and Technology,Kunming,650500,China;Key Laboratory of Unconventional Metallurgy,Ministry of Education,Kunming University of Science and Technology,Kunming,650593,China)

机构地区：[1]昆明理工大学信息工程与自动化学院,昆明650500 [2]昆明理工大学云南省人工智能重点实验室,昆明650500 [3]昆明理工大学非常规冶金教育部重点实验室,昆明650093

出　　处：《有色金属工程》2022年第5期84-93,共10页Nonferrous Metals Engineering

基　　金：国家自然科学基金资助项目(61863020)。

摘　　要：传统卷积神经网络运用于矿物种属鉴定时,由于其较大的参数量和固定输入图像分辨率的限制,需要充足的计算资源与一定的图像预处理能力,难以在实际勘探中部署。为此,基于深度可分离卷积,结合注意力机制,通过密集连接的方式构建矿物智能识别模型,且该模型可以对多分辨率矿物图像进行训练。实验结果表明,模型内存占用仅为20 Mb,验证准确率与测试准确率均高于90%,分类效果优于经典卷积神经网络,表现出优异的正负例样本鉴别能力。以上结果证明,该模型在识别性能与内存占用上达到良好的平衡,适用于便携式设备,且能有效地对不同分辨率矿物图像进行识别,并有良好的泛化性,具有潜在的应用价值。When traditional convolutional neural networks are used in mineral species identification,due to their large parameters and the limitations of fixed input image resolution,sufficient computing resources and image preprocessing are required,which are difficult to deploy in actual exploration.For this reason,based on the depth separable convolution,combined with the attention mechanism,this paper constructs a mineral intelligent recognition model through dense connection,and this model can train multi-resolution mineral images.Experimental results show that the model′s memory usage is only 20 Mb,the verification accuracy and the test accuracy are both higher than 90%,the classification effect is better than the classic convolutional neural network,and it shows excellent ability to distinguish positive and negative samples.These results show that the proposed model has fewer parameters and low memory footprint which is suitable for portable devices.This model can successfully identify mineral images with different resolutions,which has good generalization and potential application.

关 键 词：矿物分类 特征提取 多分辨率 深度学习 

分 类 号：TP391[自动化与计算机技术—计算机应用技术] P575[自动化与计算机技术—计算机科学与技术]