| 摘要: |
| 将压缩传感理论引入X射线焊缝图像缺陷判断,提出将判断X射线焊缝图像是否含有缺陷问题作为一个模式识别问题处理,将待检测图像视为样本图像的线性组合,通过求取系数向量来判断图像是否存在缺陷. 为实现系数向量的稀疏化,提出利用罚函数的方法求解0范数最小问题的近似最优解,提出新的光滑可导的0-1惩罚项函数,使求0范数最优成为可能. 在此基础上分别利用1范数最小和2范数最小求取系数向量,并利用混淆矩阵对所求结果进行分析. 结果表明,综合考虑0,1,2范数最小化所得系数的识别算法灵敏度可达99%,特异度可达98%. |
| 关键词: 缺陷检测 压缩传感 X射线 图像识别 |
| DOI： |
| 分类号: |
| 基金项目:2013陕西省自然科学资助项目(2013JQ8049);陕西省教育厅重点实验室科研计划资助项目(14JS079); 2013陕西省教育厅自然科学专项资助项目(2013JK1077);2013西安石油大学博士科研启动基金资助项目(2013BS006);中国石油科技创新基金研究资助项目(2014D-5006-0605) |
|
| A new algorithm for detecting defects of sub-arc welding x-ray image based on compress sensor theory |
|
GAO Weixin1, HU Yuheng2, WU Xiaomeng1
|
|
1.School of Electrical Engineering, Xi'an Shiyou University, Xi'an 710065, China;2.Department of Electrical and Computer Engineering, University of Wisconsin-Madison, Madison WI53705, USA
|
| Abstract: |
| An efficient X-ray radiography image analysis algorithm is developed for submerged-arc welding defects detection. The compress sensor theory is incorporated into the new algorithm, and the problem of defect detection is changed to a model recognition problem. The given X-ray image is represented by a linear combination of few model X-ray images. If a dictionary of model defect images and noise images are obtained, the coefficient vector can give important information for deciding the given image is defect or noise. Thus a sparse vector representation is sought by performing l0, l1 and l2 norm minimization. Finally, the sparse representations of the defect part and noisy part are compared in the context of a maximum likelihood ratio test which leads to the final classification. [JP2]Tested with 800 x-ray radiography images obtained from a factory production line, the proposed algorithm achieves a sensitivity 99% and specificity 98%. |
| Key words: defect detection compress sensor X-ray image recognition |
