煤泥浮选泡沫数字图象处理研究(之一)——浮选泡沫视觉特征的线邻域提取算法  

Research on Digital Image Processing of Coal Flotation Froth(Ⅰ)--The liner neighbor algorithm for extracting features of digital coal flotation froth image

作　　者：刘文礼[1] 路迈西[1] 王振翀[1] 王勇[1] 王凡[1] 

机构地区：[1]中国矿业大学化工与环境工程系,北京100083

出　　处：《中国矿业大学学报》2002年第2期120-123,共4页Journal of China University of Mining & Technology

基　　金：国家自然科学基金资助项目 ( 5 99740 32 );博士点基金项目资助 ( 19990 2 90 11)

摘　　要：进行了煤泥分批浮选实验 ,获取了大量的浮选精煤泡沫数字图象 .将图象的数字处理技术应用到泡沫图象特征参数的提取上 ,提出了有效描述浮选泡沫结构特征的线邻域提取算法——空间灰度相关矩阵法 (SGDM) ,并进一步引入了基于该灰度相关矩阵的能量、熵及惯性特征参数来描述浮选泡沫的视觉特征 .结合煤泥浮选泡沫的视觉纹理特征 ,分析了各特征参数的物理意义及其随浮选时间 (泡沫纹理 )的变化关系 。By conducting a series of coal batch cell flotation, a lot of digital images of coal flotation froth were captured. By applying digital image processing technology to the feature extraction of coal flotation froth, an effective linear neighbor algorithm--spatial gray level dependence matrix (SGDM) for extracting froth feature was presented. And based on the SGDM, a set of parameters such as energy, entropy, and inertia were proposed to describe the froth feature. By combining with the visual textural feature of coal flotation froth, the physical meaning of each parameter was explained, and the varying tendency of each parameter with flotation time (froth textural) was also analyzed. In addition, the correlation between each parameter and froth texture was pointed out qualitatively.

关 键 词：煤泥 数字图象处理 浮选泡沫 纹理 线邻域 空间灰度相关矩阵 特征参数 

分 类 号：TD923.7[矿业工程—选矿] TP391.41[自动化与计算机技术—计算机应用技术]