基于Prewitt算子与形态学的纸病图像检测方法  

PaperDefectDetectionBasedonPrewittOperatorandMathematicalMorphology

作　　者：张学兰[1,2] 李军[1,2] 辛培红[3] 李瑞瑞[1,2] 

机构地区：[1]华南理工大学制浆造纸工程国家重点实验室,广东广州510640 [2]华南理工大学广东省造纸技术与装备公共实验室,广东广州510640 [3]华南理工大学电子与信息学院新型人机交互实验室,广东广州510640

出　　处：《纸和造纸》2012年第8期25-28,共4页Paper and Paper Making

基　　金：国家重点基础研究发展规划(973计划;2010CB732205);国家科技支撑计划项目(2007BAF25B00)

摘　　要：针对Prewitt算子在检测中存在的边缘不连续性的问题,提出一种基于Prewitt算子和数学形态学的纸病图像边缘检测方法。首先利用Prewitt算子对纸病图像进行处理,然后将处理后的图像进行形态学的闭运算。实验表明,该方法结合了两种检测方法的优点,有效地提高了边缘检测的准确性,得到了比较理想的纸病边缘检测效果。A method for paper defect image detection based on Prewitt operator and mathematical morphology was presented, because the Prewitt operator is unable to make the edge consistent completely. First, the edge detection was carried out with the Prewitt operator, then the morphology operator was used to make the edge complete. Experimental results showed that the proposed method provides clearer and smoother edges than that using Prewitt operator or mathematical morphology alone, the accuracy of edge detection is improved evidently, and a much better paper defect image edge detection effect is obtained.

关 键 词：边缘检测 PREWITT算子 形态学 纸病图像 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]