摘要
现有的印刷电路板(PCB)图像去噪算法在去噪过程中容易导致边缘过度光滑和细节丢失,为了更好地提高PCB图像的去噪效果,提出了一种基于残差学习和图像差分的PCB图像去噪算法。此算法基于残差学习的思想,首先利用图像下采样方法对图像感受野进行扩大;然后设计残差块提取PCB图像噪声特征,并且在残差卷积神经网络元中加入批量归一化和ReLU激活函数,提高去噪效率;最后通过图像差分思想进行噪声去除。实验对比不同的噪声等级下各类算法的去噪性能,结果表明,所提算法在去噪评价指标峰值信噪比(PSNR)和结构相似度(SSIM)上相较于其他算法都有较好的表现。
Current printed circuit board(PCB) image-denoising algorithms can easily produce excessive edge smoothing and detail loss in the denoising process. To improve the effect of PCB image denoising, this paper proposes a PCB image-denoising algorithm based on residual learning and image difference. First, an image downsampling method is used to expand the receptive field of the image based on the idea of residual learning.Thereafter, a residual block is designed to extract the noise characteristics of the PCB image. Meanwhile, batch normalization and ReLU activation function are added to the residual convolutional neural network element to improve the denoising efficiency. Finally, the noise is removed through the image difference process. The experimental denoising performance of various algorithms is compared under different noise levels and the results show that the algorithm proposed in this paper has better performance than other algorithms in terms of peak signalto-noise ratio(PSNR) and structural similarity(SSIM).
作者
冉光再
徐雷
李大双
郭战岭
Ran Guangzai;Xu Lei;Li Dashuang;Guo Zhanling(School of Mechanical Engineering,Sichuan University,Chengdu 610065,Sichuan,China)
出处
《激光与光电子学进展》
CSCD
北大核心
2022年第12期113-120,共8页
Laser & Optoelectronics Progress
基金
四川省科技计划重点研发项目(2018GZ0108)
2017四川省省级财政智能制造专项(2017ZB073)。
关键词
图像处理
PCB图像去噪
残差学习
图像差分
感受野
下采样
image processing
PCB image denoising
residual learning
image difference
receptive field
down sampling
