作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2011, Vol. 37 ›› Issue (18): 206-208. doi: 10.3969/j.issn.1000-3428.2011.18.069

• 图形图像处理 • 上一篇    下一篇

基于小波变换的浮选泡沫图像纹理特征提取

唐朝晖,孙园园,桂卫华,刘金平   

  1. (中南大学信息科学与工程学院,长沙 410083)
  • 收稿日期:2011-03-14 出版日期:2011-09-20 发布日期:2011-09-20
  • 作者简介:唐朝晖(1965-),男,教授、博士,主研方向:智能控 制,图像处理,复杂工业过程故障诊断;孙园园,硕士研究生;桂卫华,教授;刘金平,博士研究生
  • 基金资助:
    国家自然科学基金资助项目(61071176, 60874069)

Flotation Froth Image Texture Feature Extraction Based on Wavelet Transform

TANG Zhao-hui, SUN Yuan-yuan, GUI Wei-hua, LIU Jin-ping   

  1. (School of Information Science and Engineering, Central South University, Changsha 410083, China)
  • Received:2011-03-14 Online:2011-09-20 Published:2011-09-20

摘要: 随矿物浮选工况的变化,精选泡沫表面出现亮度分布不均、灰度分布差异性大的特点,表现出明显的纹理特性。为定量分析精选泡沫表面纹理特征与浮选工况间的关系,采用小波变换方法提取纹理特征均匀度,实现精选泡沫表面纹理的量化描述,并通过实验分析,获得精选泡沫的最佳纹理区间。工业现场运行结果表明,该方法可以实时监视精选泡沫表面纹理特征变化,有利于浮选生产指标的优化 控制。

关键词: 浮选, 精选泡沫, 小波变换, 纹理特征提取, 均匀度

Abstract: With the changes in flotation conditions, fine froth show obvious texture features due to the features of uneven distribution of brightness and great difference of gray level distribution. In order to analyze the relation between texture features of bubble surface and flotation conditions, a multi-resolution analysis method based on wavelet transform is presented. This work aims to extract texture features called uniformity, achieve the quantitative description of bubble surface texture, and acquire the best texture range through analysis. Experimental results in the industrial field show that the method can realize the changes of bubble surface texture in real-time monitoring and provide a basis for production index of floatation to achieve optimal control.

Key words: flotation, fine froth, wavelet transform, texture feature extraction, uniformity

中图分类号: