基于小波与数学形态学的木材缺陷检测  

Wood defect detection using wavelet and mathematical morphology

作　　者：苏畅[1] 陈宇拓[1] 喻云水[2] 张潇云[1] 

机构地区：[1]中南林业科技大学计算机科学学院,长沙410004 [2]中南林业科技大学材料科学与工程学院,长沙410004

出　　处：《计算机工程与应用》2008年第33期246-248,共3页Computer Engineering and Applications

基　　金：湖南省科技公关计划No.2006GK3090~~

摘　　要：木材缺陷检测是木材加工中的重要步骤,为了实现木材缺陷自动检测,提出了一种基于小波与数学形态学的缺陷检测方法。首先用多尺度小波对缺陷图像进行分解,滤除缺陷图像中的干扰信息,然后进行小波重构,在重构图像上进行形态学bottomhat变换,结合阈值处理和区域生长检测出各种木材缺陷。实验表明,该方法具有高效准确的特点,能够满足木材加工过程缺陷检测的实际需求。Wood defect detection is a very important step in wood processing.In order to implement automatic detection,a method based on wavelet transform and mathematical morphology is presented in this paper.The method uses wavelet transform to suppress the interference information.Then bottom-hat transform of morphology and threshold processing are applied to get seeds in the wavelet reconstructed image.Eventually the wood defect can be segmented through region-growth algorithm.Experiments prove that this method can detect wood defect effectively and accurately and meet the requirement of wood processing.

关 键 词：木材缺陷检测 小波 数学形态学 区域生长 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]