基于自适应多尺度焊缝X光图像缺陷分割研究  

Adaptive multiscale based algorithm for defect segmentation in welding seam X-ray image

作　　者：王彦春[1] 梁德群[1] 王演[1] 邢蕴婷[1] 

机构地区：[1]大连海事大学信息科学技术学院,辽宁大连116026

出　　处：《计算机应用》2008年第11期2908-2911,共4页journal of Computer Applications

摘　　要：焊缝X光图像中的缺陷包括近似圆形和近似条形缺陷。由多尺度边缘检测理论可知:在适当尺度下,圆形缺陷在相互正交的两个方向上都是屋脊边缘,而条形缺陷只在一个方向上是屋脊边缘。利用区域一致性测度自适应确定小波滤波尺度。并在缺陷存在区域自适应确定LOG算子和方向可调滤波器的滤波尺度用以分割两种缺陷。理论分析和实验结果表明,算法有较好的分割效果。Defects in welding seam X-ray images include similar circular defects and similar bar defects. According to the theory of muhiscale edges detection, the conclusion was drawn that in appropriate scale, circular defects are considered as roof edges in two directions that are orthogonal, while bar defects are viewed as roof edges in one direction. Wavelet scales can be confirmed by region homogeneity measure in this paper. LOG operator and filter scales of steerable filters were actively ascertained in the defect areas so that the two types of defects could be segmented. Theoretical analysis and experimental results show that this algorithm is effective.

关 键 词：多尺度边缘检测 屋脊边缘 X光图像 缺陷分割 

分 类 号：TP319[自动化与计算机技术—计算机软件与理论]