论文标题 |
An edge enhancement method of radiographic weld image using bidimensional empirical mode decomposition |
作者 |
Yalin Zhao, Jianmin Gao, Changying Dang, Yulin Xiao, Zhao Wang |
发表/完成日期 |
2016-05-12 |
期刊名称 |
2016 IEEE International Conference of Online Analysis and Computing Science (ICO |
期卷 |
|
相关文章 |
|
论文简介 |
The edge and detail of radiographic weld images are fuzzy, resulting in that it is difficult to segment and recognize defects on them. So, an edge enhancement method of radiographic weld image using bidimensional empirical mode decomposition (RIEM) is proposed in this paper. In this method, first, we decompose a radiographic weld image to get its high frequency components by the bidimensional empirical mode decomposition (BEMD). Then, we perform an appropriate edge enhancement operation to the original image using high frequency information weighting, and the weighting coefficient is determined by the average detail variance (DV) and the average background variance (BV). Finally, the enhanced image with clearer edge and detail can be obtained. Experimental results show that RIEM can enhance edge and detail of the radiographic weld image effectively while maintaining its background information well. |