• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>Annual international Pittsburgh coal conference >Research on methods to differentiate coal and gangue using image processing and machine learning Weidong Wang, China University of Mining and Technology Beijing, Beijing, CHINA
【24h】

Research on methods to differentiate coal and gangue using image processing and machine learning Weidong Wang, China University of Mining and Technology Beijing, Beijing, CHINA

机译：利用图像处理和机器学习区分煤coal石的方法研究王卫东，中国矿业大学北京，北京

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Based on the issues for coal and gangue online recognition, in order to improve the degree of automation of separating coal and gangue, this paper proposes several methods that can be used to improve the differentiation of coal and gangue via image processing and machine learning. Images of coal and gangue were converted to grayscale, the background was segmented, and the contrast was stretched. A basic eigenvalue was then determined based on the contrast between the grayscale mean and the gray-level co-occurrence matrix in each image. The biorthogonal wavelet was then used to expand coal and gangue images based on discrete wavelet transforms in two dimensions (2-D), while the supplementary eigenvalue is comprised of the mean variance of the wavelet coefficient at different scales. The eigenvalue of coal was then contrasted with each gangue eigenvalue, as well as the basic and the supplementary eigenvalue to construct a mathematical recognition model based on image processing and use of a support vector machine (SVM). At the same time, coal and gangue images were directly taken as input, and a recognition model was established based on a convolutional neural network (CNN). Experimental results indicate that for coal and gangue images collected in different conditions, the recognition model based on SVM is more suitable for the recognition of small samples of coal and gangue under laboratory conditions (at a rate up to 94%). The recognition model based on CNN performs better for image recognition of large samples of coal and gangue under complex conditions (at a rate up to 99%).
机译：针对煤and石在线识别的问题，为了提高煤石分离的自动化程度，提出了几种可通过图像处理和机器学习提高煤and石区分度的方法。煤和煤石的图像被转换为​​灰度图像，背景被分割，对比度被拉伸。然后基于每个图像中灰度均值和灰度共现矩阵之间的对比度确定基本特征值。然后使用双正交小波基于二维（2-D）离散小波变换来扩展煤和煤石图像，而补充特征值则包括不同尺度下小波系数的平均方差。然后将煤的特征值与每个脉石特征值，基本特征值和补充特征值进行对比，以建立基于图像处理和支持向量机（SVM）的数学识别模型。同时，直接将煤和煤images石图像作为输入，并基于卷积神经网络（CNN）建立了识别模型。实验结果表明，对于在不同条件下采集的煤and石图像，基于支持向量机的识别模型更适合在实验室条件下识别煤samples石小样本（识别率高达94％）。基于CNN的识别模型在复杂条件下（高达99％的速率）对大型煤和煤gang石样品的图像识别性能更好。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号