基于X射线分选矿石图像的轮廓提取算法综述  

A Review of Contour Extraction Algorithms Based on X-ray Sorting Ore Images

作　　者：刘思冬 饶宇欢[1,2,3] 余新阳 范家豫[1,2] 梁毅 姚旗升 LIU Sidong;RAO Yuhuan;YU Xinyang;FAN Jiayu;LIANG Yi;YAO Qisheng(School of Resources and Environmental Engineering,Jiangxi University of Science and Technology,Ganzhou 341000,China;Jiangxi Provincial Key Laboratory of Mining Engineering,Ganzhou 341000,China;Ganzhou Jinhuan Magnetic Separation Technology Equipment Co.,Ltd.,Ganzhou 341000,China;Henan First Institute of Geology and Mineral Resources Survey Co.,Ltd.,Zhengzhou,471023,China)

机构地区：[1]江西理工大学资源与环境工程学院,江西赣州341000 [2]江西省矿业工程重点实验室,江西赣州341000 [3]赣州金环磁选科技装备股份有限公司,江西赣州341000 [4]河南省第一地质矿产调查院有限公司,郑州471023

出　　处：《有色金属工程》2023年第12期78-89,共12页Nonferrous Metals Engineering

基　　金：国家自然科学基金资助项目(52264023);江西省“双高工程”({2022}223)。

摘　　要：近年来,图像处理技术在矿石的智能分选领域广泛应用,但当前的智能分选图像处理算法在精度、算法效率和通用性等方面仍存在局限性。X射线分选矿石图像的轮廓提取是实现智能分选的重要前提之一,根据轮廓信息确定矿石中矿物分布、尺寸及形态等特征,进而优化分选流程,提高矿石的回收率,获得显著的经济效益。对X射线智能分选机的成像原理及图像噪声特性进行分析,概括了图像预处理方法并重点介绍了经典Canny算法和深度学习的HED、DeepEdge、U-Net轮廓提取算法的原理和网络结构,对算法的优势与不足进行了分析,最后提出X射线智能分选矿石图像处理算法现存的问题及今后的研究重点,为X射线智能分选图像处理系统矿物轮廓提取研究提供参考。In recent years,image processing technology has been widely used in the field of intelligent sorting of ore,but the current intelligent sorting image processing algorithms still have limitations in terms of accuracy,algorithm efficiency and versatility.The contour extraction of X-ray sorting ore image is one of the important prerequisites for intelligent sorting.The characteristics of mineral distribution,content,size and morphology in the ore are determined according to the contour information,so as to optimize the ore sorting process and improve the recovery rate and economic benefits of minerals.In this paper,the imaging principle and image noise characteristics of X-ray intelligent sorter are analyzed,the image preprocessing method is summarized,the principle and network structure of the classic canny algorithm and the HED,DeepEdge and U-Net contour extraction algorithms of deep learning are introduced,and the advantages and disadvantages of the algorithm are analyzed.Finally,the existing problems of X-ray intelligent sorting ore image processing algorithm and the future research focus are proposed.It provides a reference for the mineral contour extraction research of X-ray intelligent sorting image processing system.

关 键 词：X射线选矿 轮廓提取 CANNY算法 深度学习算法 

分 类 号：TD925[矿业工程—选矿]