印刷电路板光板缺陷图像预处理研究

为了更好地对印刷电路板光板缺陷图像进行预处理，提出了一种改进的基于全变分模型自适应图像预处理方法。分析了基于全变分范数的图像预处理模型，指出了其存在的缺点。讨论了基于L1 + p 范数的广义的全变分图像预处理模型，分析了其优点与不足之处。提出了一种改进的基于全变分模型自适应图像预处理方法，该方法能尽可能地去除印刷电路板光板缺陷图像中的噪声，同时可克服缺陷图像去噪后存在的边缘模糊与阶梯效应，使去噪后的图像得到增强且具有更加光滑、细腻的视觉效果。对实际获取的印刷电路板光板缺陷图像采用四种图像预处理方法或模型进行了主观与客观实验比较，结果表明，该方法对印刷电路板光板缺陷图像预处理有较好的效果。而且，针对不同的印刷电路板光板缺陷采用该方法都能很好地检测出结果。

Abstract

In order to actualize image preprocessing of defect image on printed circuit board better, an improved self-adaptive image preprocessing method based on the total variation model is proposed. The image preprocessing model based on the total variation norm is analyzed, and its shortcomings are pointed out. The generalized total variation image preprocessing model based on L1 + p norms is discussed, the advantages and disadvantages are analyzed. An improved self-adaptive image preprocessing method based on the total variation model is proposed, the defect image noise of printed circuit board can be eliminated as far as possible by using the proposed method. At the same time, the edge faintness and ladder effect existed in the defect image can be overcomed better after denoising, and the image after denoising has more slippery and exquisite visual effects. The subjective and objective experimental comparisons among the four image preprocessing methods or models are achieved aiming at the defect image of actual printed circuit board, and the result indicates that the proposed method has good effect on defect image preprocessing of printed circuit board. What is more, the results are all detected better by adopting the proposed method for different printed circuit board defects.

参考文献

[1] 乔闹生, 叶玉堂, 莫春华, 等. 印刷电路板光电图像获取与预处理研究[J].光学学报,2010, 30(4): 984-988.

Qiao Naosheng, Ye Yutang, Mo Chunhua, et al.. Study of capturing and preprocessing of printed circuit board photoelectric image [J]. Acta Optica Sinica, 2010, 30(4): 984-988.

[2] 乔闹生, 孙萍. 印制电路板线路检测研究[J]. 光子学报, 2013, 42(11): 1355-1359.

Qiao Naosheng, Sun Ping. Circuitry detection in printed circuit board [J]. Acta Photonica Sinica, 2013, 42(11): 1355-1359.

[3] 乔闹生, 叶玉堂, 莫春华, 等. 印刷电路板圆孔光电图像的同心圆检测方法[J]. 光学学报, 2010, 30(1): 75-78.

Qiao Naosheng, Ye Yutang, Mo Chunhua, et al.. Method for the detection of concentric circles of photoelectric image of circular hole in printed circuit board [J]. Acta Optica Sinica, 2010, 30(1): 75-78.

[4] 李莹莹, 张志毅, 袁林. 线结构光光条中心提取综述[J]. 激光与光电子学进展, 2013, 50(10): 100002.

Li Yingying, Zhang Zhiyi, Yuan Lin. Survey on linear structured light stripe center extraction [J]. Laser & Optoelectronics Progress, 2013, 50(10): 100002.

[5] Rudin L I, Osher S, Fatemi E. Nonlinear total variation based noise removal algorithms [J]. Physica D, 1992, 60(1): 259-268.

[6] Alliney S. A property of the minimum vectors of a regularizing functional defined by means of the absolute norm [J]. IEEE Transactions on Signal Processing, 1997, 45(4): 913-917.

[7] Nikolova M. Minimizers of cost-functions involving nonsmooth data fidelity terms Application to the processing of outliers [J]. SIAM J Numer Anal, 2002, 40(3): 965-994.

[8] Song B. Topics in Variational PDE Image Segmentation, Inpainting and Denoising [D]. Los Angeles: University of California Los Angeles, 2003.

[9] Osher S, Burger M, Goldfarb D, et al.. An iterative regularization method for total variation based image restoration [J]. Multiscale Modeling and Simulation, 2005, 4(2): 460-489.

[10] Marzek P, Weickert J. From two-dimensional nonlinear diffusion to coupled Haar wavelet shrinkage [J]. J Vis Commun Image R, 2007, 18(2): 162-175.

[11] Yin W, Goldfarb D, Osher S. The total variation regularized L1 model for multiscale decomposition [J]. Multiscale Modeling and Simulation, 2007, 6(1): 190-211.

[12] 邵晓鹏, 钟宬, 杜娟, 等. 多值压缩编码孔径超分辨率成像方法[J]. 光电子·激光, 2012, 23(6): 1189-1195.

Shao Xiaopeng, Zhong Cheng, Du Juan, et al.. Super-resolution imaging method using multi-value compressed coded aperture [J]. Journal of Optoelectronics·Laser, 2012, 23(6): 1189-1195.

[13] Acar R, Vogel C R. Analysis of bounded variation penalty methods for ill-posed problems [J]. Inverse Problems, 1994, 10(6): 1217-1229.

[14] 乔闹生, 邓磊, 曾友兵, 等. 含噪声且较模糊的印刷电路板光电图像边缘检测研究[J]. 光电子·激光, 2013, 24(4): 740-745.

Qiao Naosheng, Deng Lei, Zeng Youbing, et al.. Study of noisy and darker PCB photoelectricity image edge detection [J]. Journal of Optoelectronics·Laser, 2013, 24(4): 740-745.

[15] 周志盛, 相里斌, 张文喜, 等. 基于迭代的傅里叶望远镜图像重构方法[J]. 光学学报, 2014, 34(5): 0511005.

Zhou Zhisheng, Xiangli Bin, Zhang Wenxi, et al.. Image reconstruction method of Fourier telescope based on iteration [J]. Acta Optica Sinica, 2014, 34(5): 0511005.

[16] 陈超, 赵生妹. 高阶差值筛选鬼成像方案研究[J]. 光学学报, 2014, 34(6): 0611002.

Chen Chao, Zhao Shengmei. Study on high order difference sifted ghost imaging scheme [J]. Acta Optica Sinica, 2014,34(6): 0611002.

[17] 张宝华, 刘鹤. 采用子带分量阈值估计的红外图像去噪方法[J]. 中国激光, 2014, 41(8): 0809002.

Zhang Baohua, Liu He. Infrared image denoising algorithm based on sub-band component threshold estimation [J]. Chinese J Lasers, 2014, 41(8): 0809002.

[18] 钱方, 孙涛, 郭劲, 等. 基于特征点分布特性的激光干扰效果评估算法[J]. 中国激光, 2014, 41(5): 0509001.

Qian Fang, Sun Tao, Guo Jin, et al.. Assessment algorithm of laser-dazzling effects based on the feature-point distributing characteristic [J]. Chinese J Lasers, 2014, 41(5): 0509001.

[19] 高山, 李成, 毕笃彦. 有效滤除高强度图像混合噪声的方法[J]. 计算机辅助设计与图形学报, 2012, 24(5): 656-661.

Gao Shan, Li Cheng, Bi Duyan. An effective method of high-intensity mixed noise filtering for images [J]. Journal of Computer-Aided Design & Computer Graphics, 2012, 24(5): 656-661.

乔闹生, 张奋, 黎小琴. 印刷电路板光板缺陷图像预处理研究[J]. 激光与光电子学进展, 2015, 52(2): 021003. Qiao Naosheng, Zhang Fen, Li Xiaoqin. Defect Image Preprocessing of Printed Circuit Board[J]. Laser & Optoelectronics Progress, 2015, 52(2): 021003.

印刷电路板光板缺陷图像预处理研究

关于本站 Cookie 的使用提示

全站搜索

印刷电路板光板缺陷图像预处理研究

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索