基于CCHS的浮选泡沫图像纹理特征提取  

Flotation froth image texture extraction based on CCHS

作　　者：陈宁[1] 林霞[1] 桂卫华[1] 阳春华[1] 唐朝晖[1] 

机构地区：[1]中南大学信息科学与工程学院,湖南长沙410083

出　　处：《中南大学学报（自然科学版）》2013年第11期4506-4512,共7页Journal of Central South University:Science and Technology

基　　金：国家自然科学基金资助项目(61134006;61071176)

摘　　要：为了快速、有效地获取图像的纹理特征,提出一种基于颜色共生混合结构(color co-occurrence hybrid structure,CCHS)的浮选泡沫图像纹理特征提取方法。该方法的步骤如下:首先,将泡沫图像从RGB空间转换到HSI空间并对各颜色分量进行量化,计算图像的颜色共生矩阵并将其正规化为三角矩阵;然后,利用CCHS算法提取图像的纹理特征;最后,分析矿物品位与特征统计量熵及新特征参数即纹理复杂度之间的变化关系。研究结果表明:适当提高颜色分量的量化级数能提高浮选泡沫图像纹理特征提取的精确度;利用CCHS算法提取纹理特征,降低了计算的复杂度;实验结果验证了该算法的有效性,表明它能更准确地对矿物品位进行调控,指导浮选工况。A method for froth image texture extraction based on CCHS was proposed to rapidly and effectively extract feature texture. The procedures are as follows. Firstly, froth image space was converted from RGB to HSI in which each color component was quantized. Then the color co-occurrence matrix was calculated and froth image texture features were extracted from the normalized triangle matrix using CCHS algorithm. Finally, the relationships between concentrate grade and both statistical entropy and texture complexity were analyzed. The results show that the quantization degree of color components is appropriately increased, which increases the flotation froth image texture extraction accuracy. Using the extraction method of CCHS algorithm can reduce the calculation complexity. The experimental results verify the validity of this method, it can more accurately regulate and control the mineral grade and guide the flotation operation.

关 键 词：浮选 泡沫图像 纹理特征提取 颜色共生混合结构 矿物品位 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]