基于多重分形理论的原木CT腐朽图像分析与处理  

Analysis and Processing of Decayed Log CT Image Based on Multifractal Theory

作　　者：韩书霞[1] 戚大伟[1] 于雷[1] 

机构地区：[1]东北林业大学,哈尔滨150040

出　　处：《森林工程》2007年第5期15-18,共4页Forest Engineering

基　　金：国家林业局948项目资助(2002-39(2));黑龙江省博士后启动金项目资助

摘　　要：使用计算机断层扫描技术进行原木无损检测,采用多重分形频谱分析方法可以对原木CT图像进行有效的边缘检测,该方法首先计算图像各像素点的H lder指数α(x,y),然后估计出其多重分形频谱f(α)的值,对图像的像素点进行分类,f(α)=1为平滑边缘点,1≤f(α)<1.5为奇异边缘点。根据多重分形理论,平滑点和奇异点的集合即为图像的边缘点。实验结果表明,该方法对原木CT图像的边缘检测具有良好的效果,并具有较好的局部性,为原木CT图像的边缘检测提供了一种新方法。Computed tomography technology was used for the log nondestructive testing, a method was adopted to detect the edge effectively in log CT image based on mtdtifractal analysis in this paper. The Holder exponent of image pixels was calcttlated first, then its muhifractal spectrum was estimated and different image pixels were classified, f（α） = 1, smoothing edge points;1≤f（α） 〈 1.5, singular edge points. Based on multifractal theory, the set of both singular edge points and smoothing edge points is the set of image edge points. Experiment results showed that this method of log CT image edge detection was a more effective and more local method. It provided a new method for log CT edge detection.

关 键 词：多重分形 Holder指数 边缘检测 原木CT图像 

分 类 号：S781.1[农业科学—木材科学与技术]