矿物显微图像中网孔状及针板状成分识别方法研究  

An Approach of Mesh and Striation Texture Recognition for Ore Microscope Image Classification

作　　者：游劲敏[1] 李咸伟[2] 沈红标[2] 刘其真[1] 

机构地区：[1]复旦大学计算机科学与工程系,上海200433 [2]宝山钢铁股份有限公司研究院环境与资源研究所,上海201900

出　　处：《中国图象图形学报》2006年第11期1690-1694,共5页Journal of Image and Graphics

摘　　要：矿石的显微图像成分分析是一项具有挑战性的应用研究课题,针对所要求的对某种矿石进行自动识别的任务,提出了一种使用改进的统计假说方法对网孔状纹理成分进行识别的方法;并提出了一种采用Sobel变换、骨架提取以及Hough变换相结合的技术进行针板状纹理成分识别的方法,实验结果表明,该方法是有效的。The ingredient analysis of ore microscope image is a challenging research area. To accomplish automatic recognition task on a kind of ore, this paper proposed an improved statistical hypothesis method for mesh texture ingredient recognition; and with Sobel edge detection, Skeleton Extraction, Hough Transformation another method is proposed on the recognition for needle like or striation texture ingredient. The experimental results show that the methods proposed in this paper are efficient.

关 键 词：矿石纹理 统计假说 边缘检测 HOUGH变换 骨架提取 图像分割 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]