Detection for transverse corner cracks of steel plates’ surface using wavelet
Qiong ZHOU, Qi AN
Detection for transverse corner cracks of steel plates’ surface using wavelet
An algorithm is presented for detecting transverse corner cracks at a steel plate surface using wavelet transform. According to characteristics of transverse corner crack images, the wavelet transform is used for the multi-scale analysis of detecting the image edges and disintegrating the image into four directions at the same time. The proper threshold value is chosen to segment the image into vertical components to obtain the final detection result. The experiment shows that transverse corner cracks of steel plates can be more effectively extracted by the proposed method than the other two common methods.
transverse corner cracks / defect detection / multi-scales wavelet analysis
[1] |
Liu Yuxiang. The analysis of the cause of defects on steel plates’ surface and the prevention measures. Jiugang Keji, 2002, 2: 19-22(in Chinese)
|
[2] |
Zhai Jiayun, Zhang Yuping. Analysis of images in detecting flaws on the surface of steel slabs. Shanxi Metallurgy, 2003, 1: 23-24(in Chinese)
|
[3] |
Wei Ying, Shi Zelin, Li Chengjun, Yu Haibin. Detection algorithm for infrared small target in background of sea and sky. Infrared and Laser Engineering, 2003, 2(32): 153-156(in Chinese)
|
[4] |
Chen Wufan. Wavelet Analysis and Application in Image Processing. Beijing: Scientific Publishing House, 2002(in Chinese)
|
[5] |
Zhang Yujin. Image Segmentation. Beijing: Scientific Publishing House, 2001(in Chinese)
|
[6] |
Mallat S. A theory of multiresolution signal decom-position: the wavelet representation. IEEE Trans Pattern Anal Machine Intell, 1989, 1l: 674-693
CrossRef
Google scholar
|
[7] |
Mallat S. Wavelets for a vision. In: Proc IEEE, 1996, 84: 604-614
CrossRef
Google scholar
|
[8] |
Su Zhihong. Analysis of the reasons for transverse corner cracks on the steel billets. Metallurgy Series, 2001, 4: 20-22, 19 (in Chinese)
|
[9] |
Hu Min, Chen Qianghong. Selection and comparison of four typical wavelet bases in the multi-scales analysis. Microcomputer Development, 2002, 3: 41-43, 44 (in Chinese)
|
/
〈 | 〉 |