基于LBP特征与SVM的煤矸识别方法研究  

Research on Coal Gangue Identification Method Based on LBP Feature and SVM

作　　者：程刚[1,2] 陈杰 何磊 CHENG Gang;CHEN Jie;HE Lei(State Key Laboratory of Mining Response and Disaster Prevention and Control in Deep Coal Mines,Anhui University of Science and Technology,Huainan 232001,China;School of Mechanical Engineering,Anhui University of Science and Technology,Huainan 232001,China)

机构地区：[1]安徽理工大学深部煤矿采动响应与灾害防控国家重点实验室,安徽准南232001 [2]安徽理工大学机械工程学院,安徽淮南232001

出　　处：《煤炭技术》2023年第10期12-15,共4页Coal Technology

基　　金：安徽省高校协同创新项目(GXXT-2021-076)。

摘　　要：为了提高煤炭开采过程中煤和矸石识别的准确率,提出了一种基于LBP特征与SVM的煤矸识别方法。首先利用机器视觉技术采集煤和矸石的图像,然后对煤和矸石图像进行中值滤波、图像锐化和阈值分割处理,再进行特征提取,最后分别用SVM、GA-SVM、PSO-SVM分类器进行分类识别。试验结果表明,LBP特征提取结合PSO-SVM分类器的识别效果最好,PSO-SVM模型的训练集和测试集的平均准确率分别为95.62%和94.06%,有效提高了煤矸识别的分类准确率。To improve the accuracy of coal and gangue identificationduring coal mining, a method of coal and gangue identification based on LBP feature and SVM is proposed. Firstly, the images of coal and gangue are collected by machine vision technology, and then the images of coal and gangue are processed by median filtering, image sharpening and threshold segmentation, and next the features are extracted.Finally, SVM, GA-SVM and PSO-SVM classifiers are used for classification and identification. The experimental results show that LBP feature extraction combined with PSO-SVM classifier has the bestidentification effect, and the average accuracy of the training set and test set of the PSO-SVM model are 95.62% and 94.06%, respectively, and effectively improve the accuracy of coal gangue identification and classification.

关 键 词：煤矸识别 图像处理 LBP特征 SVM分类 

分 类 号：TD94[矿业工程—选矿]