首页 | 本学科首页   官方微博 | 高级检索  
     

基于改进CV模型和PCNN的NSST域焊接缺陷提取
引用本文:文方青,叶志龙,张弓. 基于改进CV模型和PCNN的NSST域焊接缺陷提取[J]. 光学仪器, 2015, 37(1): 57-64
作者姓名:文方青  叶志龙  张弓
作者单位:1. 南京航空航天大学电子信息工程学院,江苏南京210016;南京航空航天大学雷达成像与微波光子技术教育部重点实验室,江苏南京210016
2. 上海航天控制技术研究所,上海,200233
基金项目:国家自然科学基金(61071163,61271327);南京航空航天大学博士学位论文创新与创优基金(BCXJ14-08);江苏省研究生培养创新工程(KYLX_0277);中央高校基本科研业务费专项资金资助;江苏高校优势学科建设工程(PADA)
摘    要:为了精确地提取焊接缺陷,进一步提高缺陷检测的准确性,提出了一种基于改进ChanVese(CV)模型和脉冲耦合神经网络(pulse coupled neural network,PCNN)的非下采样Shearlet变换(non-subsampled Shearlet transform,NSST)域焊接缺陷提取方法。首先,对焊接缺陷图像进行NSST分解,对得到的低频分量采用PCNN提取出缺陷的主要区域;然后,利用背景抑制后的低频分量和高频分量构造出高频特征图像,并对其进行粗分割,再利用改进的CV模型寻找最优轮廓,提取出缺陷精细轮廓;最后,融合缺陷的主要区域和精细轮廓信息得到最终的结果。实验结果表明,与其他缺陷提取法相比,所用方法提取的缺陷结构更为完整,缺陷轮廓更为精细。

关 键 词:焊接缺陷  轮廓提取  非下采样Shearlet  改进的CV模型  脉冲耦合神经网络
收稿时间:2014-07-16

Extraction of welding defect based on improved CV model and PCNN in non-subsampled Shearlet domain
WEN Fangqing,YE Zhilong and ZHANG Gong. Extraction of welding defect based on improved CV model and PCNN in non-subsampled Shearlet domain[J]. Optical Instruments, 2015, 37(1): 57-64
Authors:WEN Fangqing  YE Zhilong  ZHANG Gong
Affiliation:College of Electronic and Information Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China;Key Laboratory of Radar Imaging and Microwave Photonics(MOE), Nanjing University of Aeronautic and Astronautics, Nanjing 210016, China;Institute of Spaceflight Control Technology, Shanghai 200233, China;College of Electronic and Information Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China;Key Laboratory of Radar Imaging and Microwave Photonics(MOE), Nanjing University of Aeronautic and Astronautics, Nanjing 210016, China
Abstract:In order to extract welding defect more accurately and further improve the accuracy of defect detection, a welding defect extraction method based on improved Chan-Vese(CV)model and pulse coupled neural network(PCNN)in the non-subsampled Shearlet transform(NSST)domain is proposed. Firstly, a welding defect image is decomposed by NSST. The main region of defect is obtained through processing low-frequency component by using PCNN. Then, high-frequency feature image is constructed through low-frequency after background suppression and high-frequency, and improved CV model is used to search optimal contour of defect after coarse segmentation. Finally, the final defect is extracted by fusing main region and fine contour of welding defect. Compared with recently proposed defect extraction methods, the extracted welding defect using the proposed method has more complete structure and optimal contour.
Keywords:welding defect  contour extraction  non-subsampled Shearlet  improved CV model  pulse coupled neural network
本文献已被 CNKI 万方数据 等数据库收录!
点击此处可从《光学仪器》浏览原始摘要信息
点击此处可从《光学仪器》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号