摘要
花岗岩薄片不同矿物成分在图像中可能存在相同灰度分布甚至相似纹理。通过结合正交偏光镜镜下图片干涉色信息和单偏光镜图片信息分析,提高了花岗岩薄片石英分割的准确率。方法是从单偏光镜和正交偏光镜下图片中提取图像块的特征信息,运用支持向量机分类方法对图像块进行分类,在分类为石英的图像块中选取种子,再根据两张图片信息,用区域生长方法完成石英分割。该方法实现了自动化分割,分割准确率高,实验证明该方法切实可行。
To improve the accuracy of flake image segmentation, we made a study on segmentation of quartz from granite flake image, with a image shot under a polarized light microscope and a counterpart under perpendicular polarized light microscope. First, classify image blocks by means of SVM. Then plant a seed in each object image block, and employ region growth method to get the result segmented image. The two image＇s features were well apprehended by the approach. It is proved by experiments that this method is effective,
出处
《科技广场》
2008年第10期108-111,共4页
Science Mosaic
