PCB图像的自适应全变分去噪算法  

An Adaptive Total Variation Denoising Algorithm for Printed Circuit Board Images

作　　者：余丽红[1] 曹蕾[1] 柳贵东 杨新盛[1] 黄东升 YU Lihong;CAO Lei;LIU Guidong;YANG Xinsheng;HUANG Dongsheng(Electronic and Information Engineering Department,Guangdong Baiyun University,Guangzhou 510450,China)

机构地区：[1]广东白云学院电气与信息工程学院,广州广东510450

出　　处：《红外技术》2018年第9期875-880,共6页Infrared Technology

基　　金：国家自然科学基金资助项目(61174098);广东省教育厅2017年重点平台及科研项目(青年创新人才类项目(自然科学类))(2017KQNCX224);2017年广东省省级科技重大专项资助项目(2017B090914001)

摘　　要：为了提高印刷电路板(PCB)图像的去噪效果,提出了一种基于先验信息的PCB图像自适应去噪算法。首先,采用非局部均值滤波算法对模糊的PCB图像进行滤波以减少图像噪声,并提取去噪后的图像先验信息。其次,在全变分算法的基础上,设计基于先验信息的自适应正则化参数。最后,利用迭代正则化算法快速得到最优的去噪图像。实验结果和数据分析证实了所提算法的有效性。与原有算法相比,所提算法能够得到视觉效果更好的去噪图像,信噪比也比原有方法提高至少0.5 dB,结构相似度指标也有相应的提升。To improve the denoising effect of printed circuit board(PCB)images,an adaptive denoising algorithm based on prior information for PCB images is proposed in this paper.First,a non-local mean filter is used to reduce noise from the blurred PCB images and extract the prior information from the denoised images.Second,a total variation adaptive regularization parameter based on prior information is designed.Finally,an iterative regularization algorithm is used to obtain the optimal denoising image quickly.Experimental results and data analysis confirm the effectiveness of the proposed algorithm.Compared with the original algorithm,the proposed algorithm can obtain a better visual effect.The signal-to-noise ratio was increased up to 0.5 dB,and the structure similarity also showed corresponding improvement.

关 键 词：图像去噪 全变分 非局部均值滤波 自适应去噪 

分 类 号：TP751.1[自动化与计算机技术—检测技术与自动化装置]