基于深度图像分析的细粒度矿石分级测定方法

doi:10.3969/j.issn.0255-8297.2019.04.006

应用科学学报 ›› 2019, Vol. 37 ›› Issue (4): 490-500.doi: 10.3969/j.issn.0255-8297.2019.04.006

基于深度图像分析的细粒度矿石分级测定方法

卢才武, 齐凡, 阮顺领

西安建筑科技大学管理学院, 西安 710055

收稿日期:2018-06-12 修回日期:2018-12-21 出版日期:2019-07-31 发布日期:2019-10-11
作者简介:卢才武,教授,博导,研究方向:图像检测、模式识别及矿业系统工程,E-mail:xjdkslu@163.com
基金资助:
国家自然科学基金（No.51774228）；陕西省自然科学基金（No.2017JM5043）资助

Grade Determination of Fine Grain Ore Based on Depth Image Analysis

LU Caiwu, QI Fan, RUAN Shunling

School of Management, Xi'an University of Architecture and Technology, Xi'an 710055, China

Received:2018-06-12 Revised:2018-12-21 Online:2019-07-31 Published:2019-10-11

摘要/Abstract

摘要： 针对图像处理技术在细粒度矿石分级测定时存在的精度不足问题，提出基于深度图像分析的分级测定方法.在灰度共生矩阵（gray-level co-occurrence matrix，GLCM）的基础上提出点对生成步长与图像灰度压缩等级的自适应选取方法，通过网格搜索与交叉验证来优化支持向量机（support vector machine，SVM）分类器，提高粒度测定精度.实验结果表明，该方法对0~0.9 mm、0.9~3.0 mm、3.0~5.0 mm、5.0~7.0 mm这4种等级的细粒度矿石分级准确率可达92%以上，能够充分满足细粒度矿石分级测定的要求.

关键词: 矿石粒度, 纹理提取, 图像分类, 灰度共生矩阵, 最大线性离散度

Abstract: To improve the precision of image processing technology in fine-grained ore measurement, a grading determination method based on depth image analysis is proposed. On the basis of gray-level co-occurrence matrix (GLCM), a maximum linear dispersion method is proposed to generate the step size and gray-level compression level adaptively, and support vector machine (SVM) classifiers are optimized through grid search and crossvalidation thus to improve the accuracy of particle size measurement. Experimental results showed that this method can achieve an accuracy rate of more than 92% for fine-grained ores with particle sizes of 0~0.9 mm, 0.9~3.0 mm, 3.0~5.0 mm and 5.0~7.0 mm, which can fully meet the requirements of grading and determining fine-grained ores.

Key words: ore grain size, texture extraction, image classification, gray-level co-occurrence matrix, maximum linear dispersion

中图分类号:

TP391.4

卢才武, 齐凡, 阮顺领. 基于深度图像分析的细粒度矿石分级测定方法[J]. 应用科学学报, 2019, 37(4): 490-500.

LU Caiwu, QI Fan, RUAN Shunling. Grade Determination of Fine Grain Ore Based on Depth Image Analysis[J]. Journal of Applied Sciences, 2019, 37(4): 490-500.

参考文献

[1] 刘彦伟,刘明举. 粒度对软硬煤粒瓦斯解吸扩散差异性的影响[J]. 煤炭学报,2015, 40(3):579-587. Liu Y W, Liu M J. Effect of particle size on difference of gas desorption and diffusion between soft coal and hard coal[J]. Journal of China Coal Society, 2015, 40(3):579-587. (in Chinese)
[2] Andersson T, Thurley M J, Carlson J E. A machine vision system for estimation of size distributions by weight of limestone particles[J]. Minerals Engineering, 2012, 25(1):38-46.
[3] Ko Y D, Shang H. A neural network-based soft sensor for particle size distribution using image analysis[J]. Powder Technology, 2011, 212(2):359-366.
[4] Soppela I, Airaksinen S, Hatara J, RäIkkönen H, Antikainen O, Yliruusi J, Sandler N. Rapid particle size measurement using 3D surface imaging[J]. Aaps Pharmscitech, 2011, 12(2):476-484.
[5] 蔡改贫,李龙茂,姜志宏. 基于图像处理的矿石粒度检测系统设计[J]. 冶金自动化,2013, 37(6):63-66. Cai G P, Li L M, Jiang Z H. Design of ore particle size measurement system based on image processing[J]. Metallurgical Industry Automation, 2013, 37(6):63-66. (in Chinese)
[6] 商梦石,贾瑞强,张海林. 图像处理技术在矿石粒度检测中的应用[J]. 矿产综合利用,2016(6):13-16. Shang M S, Jia R Q, Zhang H L. Application of image processing technology in ore particle size measurement[J]. Multipurpose Utilization of Mineral Resources, 2016(6):13-16. (in Chinese)
[7] 董珂,蒋大林. 基于改进分水岭变换的矿石图像分割算法[J]. 计算机工程与设计,2013, 34(3):899-903. Dong K, Jiang D L. Ore image segmentation algorithm based on improved watershed transform[J]. Computer Engineering and Design, 2013, 34(3):899-903. (in Chinese)
[8] 栾丽华,郭连军. 基于线性变换与多种平滑去噪的爆堆图像增强方法[J]. 爆破,2011, 28(1):33-34. Luan L H, Guo L J. A blasting lumps image enhancement method based on linear transformation and some of smoothness[J]. Blasting, 2011, 28(1):33-34. (in Chinese)
[9] Kistner M, Jemwa G T, Aldrich C. Monitoring of mineral processing systems by using textural image analysis[J]. Minerals Engineering, 2013, 52(5):169-177.
[10] Aldrich C, Uahengo F D L, Kistner M. Estimation of particle size in hydrocyclone underflow streams by use of multivariate image analysis[J]. Minerals Engineering, 2015, 70:14-19.
[11] Aligholi S, Khajavi R, Razmara M. Automated mineral identification algorithm using optical properties of crystals[M]. Pergamon Press, Inc. 2015.
[12] Liu Y, Yu F. An automatic image fusion algorithm for unregistered multiply multi-focus images[J]. Optics Communications, 2015, 341:101-113.
[13] Haralick R M, Shanmugam K, Dinstein I. Textural features for image classification[J]. IEEE Transactions on Systems Man & Cybernetics, 1973, SMC-3(6):610-621.
[14] 邹承明,薛栋,郭双双,赵广辉. 一种改进的图像相似度算法[J]. 计算机科学,2016, 43(6):72-76. Zou C M, Xue D, Guo S S, Zhao G H. Improved image similarity algorithm[J]. Journal of Computer Science, 2016, 43(6):72-76. (in Chinese)
[15] 方志坚,傅仰耿,陈建华. 纹理图像分类的置信规则库推理方法[J]. 应用科学学报,2017, 35(5):545-558. Fang Z J, Fu Y G, Chen J H. Belief rule base inference for texture image classification[J]. Journal of Applied Sciences, 2017, 35(5):545-558. (in Chinese)
[16] Zhang X, Cui J, Wang W, Lin C. A study for texture feature extraction of high-resolution satellite images based on a direction measure and gray level co-occurrence matrix fusion algorithm[J]. Sensors, 2017, 17(7):1474-1489.
[17] Kuffer M, Pfeffer K, Sliuzas R, Baud I. Extraction of slum areas from VHR imagery using GLCM variance[J]. IEEE Journal of Selected Topics in Applied Earth Observations & Remote Sensing, 2016, 9(5):1830-1840.
[18] 王昊鹏,李慧. 基于局部二值模式和灰度共生矩阵的籽棉杂质分类识别[J]. 农业工程学报,2015, 31(3):236-241. Wang H P, Li H. Classification recognition of impurities in seed cotton based on local binary pattern and gray level co-occurrence matrix[J]. Transactions of the Chinese Society of Agricultural Engineering, 2015, 31(3):236-241. (in Chinese)
[19] 熊邦书,刘雨,莫燕,黄建萍,李新民. 基于SVM的直升机飞行状态识别[J]. 应用科学学报,2016, 34(4):469-474. Xiong B S, Liu Y, Mo Y, Huang J P, Li X M. Recognition of helicopter flight condition based on support vector machine[J]. Journal of Applied Sciences, 2016, 34(4):469-474. (in Chinese)
[20] Yu H, Gao L, Liao W, Zhang B, Pižurica A, Philips W. Multiscale superpixel-level subspace-based support vector machines for hyperspectral image classification[J]. IEEE Geoscience & Remote Sensing Letters, 2017, 14(11):1-5.

基于深度图像分析的细粒度矿石分级测定方法

Grade Determination of Fine Grain Ore Based on Depth Image Analysis

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 7

编辑推荐

Metrics

本文评价

[1]	司广文, 秦川, 姚恒, 韩彦芳, 张志超. 基于纹理特征分类与合成的鲁棒无载体信息隐藏[J]. 应用科学学报, 2020, 38(3): 441-454.
[2]	汪然, 牛少彰, 平西建, 张涛, 桑晓丹. 降低特征类内离散度的JPEG图像隐写分析[J]. 应用科学学报, 2019, 37(1): 41-50.
[3]	宋海峰, 陈广胜, 景维鹏, 杨巍巍. 基于(2D)²PCA的受限玻尔兹曼机图像分类算法及其并行化实现[J]. 应用科学学报, 2018, 36(3): 495-503.
[4]	董伟, 王建军. 改进的卷积神经网络用于对比度增强取证[J]. 应用科学学报, 2017, 35(6): 745-753.
[5]	方志坚, 傅仰耿, 陈建华. 纹理图像分类的置信规则库推理方法[J]. 应用科学学报, 2017, 35(5): 545-558.
[6]	黄杰，倪鹏宇. 基于人体关键部位的不良图像过滤[J]. 应用科学学报, 2014, 32(4): 416-422.
[7]	付仲良，张文元，孟庆祥. 灰度和纹理特征组合的SAR影像SVM分类[J]. 应用科学学报, 2012, 30(5): 498-504.