基于降采样和相位相关的印刷电路板图像配准

陈思摇; 伍世虔

Chinese

您当前的位置：

首页 >

文章列表页 >

基于降采样和相位相关的印刷电路板图像配准

更新时间：2026-09-04

- 基于降采样和相位相关的印刷电路板图像配准
- Printed circuit board image alignment based on downsampling and phase correlation
- 微电子学与计算机 2021年38卷第4期页码：17-22
- 作者机构：
  
  武汉科技大学信息科学与工程学院,湖北,武汉,430081
- 作者简介：
- 基金信息：
  
  国家自然科学基金项目 61775172
- DOI：
  中图分类号：
- 纸质出版：2021
- 稿件说明：
移动端阅览
陈思摇, 伍世虔. 基于降采样和相位相关的印刷电路板图像配准[J]. 微电子学与计算机, 2021, 38(4): 17-22.

CHEN Si-yao, WU Shi-qian. Printed circuit board image alignment based on downsampling and phase correlation[J]. 2021, 38(4): 17-22.
陈思摇, 伍世虔. 基于降采样和相位相关的印刷电路板图像配准[J]. 微电子学与计算机, 2021, 38(4): 17-22. DOI：

CHEN Si-yao, WU Shi-qian. Printed circuit board image alignment based on downsampling and phase correlation[J]. 2021, 38(4): 17-22. DOI：

摘要

针对PCB缺陷检测系统对配准的要求，提出了一种基于图像降采样和相位相关法的配准算法.首先，为了解决使用单侧峰的相位相关亚像素配准方法在整数位移处误差较大的问题，提出根据两侧峰峰值差值占主峰的比例来判断是否需要使用双侧峰法修正的方法; 其次，为了解决算法应用中的效率问题，讨论了不同降采样倍率对配准速度和精度的影响.实验结果表明，该改进算法的最大误差和平均误差均比原单侧峰法小; 二千万像素的图像在五倍降采样情况下就能获得高精度，且速度约有20倍提升，该算法具有鲁棒性和实时性.

Abstract

A registration algorithm based on image downsampling and phase correlation was proposed to meet the registration requirements of PCB defect detection system. First of all

in order to solve the problem that the phase-dependent sub-pixel registration method using one-sided peak has a large error at the integer displacement

a two-side peak method is proposed to judge whether it is necessary to use the two-side peak method according to the ratio of the peak-to-peak difference between the two sides to the main peak. Secondly

in order to solve the efficiency problem in the application of algorithms

the effects of different downsampling magnifications on registration speed and accuracy are discussed. The experimental results show that the maximum error and average error of the improved algorithm are smaller than that of the one-sided peak method. The 20-million-pixel image can achieve high accuracy under the condition of five times of downsampling

and the speed is improved by about 20 times. The algorithm has robustness and real-time performance.

关键词

Keywords

references

FOROOSH H, ZERUBIA J B, BERTHOD M. Extension of phase correlation to subpixel registration[J]. IEEE Transactions on Image Processing, 2002, 11(3): 188-200. DOI: 10.1109/83.988953.

刘政, 熊昊, 肖森林, 等. 基于PCA和分段RHT的PCB板圆Mark点定位[J]. 重庆理工大学学报(自然科学), 2017, 31(1): 93-99. DOI: 10.3969/j.issn.1674-8425(z).2017.01.015. LIU Z, XIONG H, XIAO S L, et al. Positioning of circular mark in PCB based on PCA and segment RHT[J]. Journal of Chongqing University of Technology (Natural Science), 2017, 31(1): 93-99. DOI: 10.3969/j.issn.1674-8425(z).2017.01.015.

DONG Z N, CHEN L J. Image registration in PCB fault detection based on infrared thermal imaging[C]//2019 Chinese Control Conference (CCC). Guangzhou, China: IEEE, 2019: 4819-4823. DOI: 10.23919/ChiCC.2019.8866191.

HUA G L, HUANG W P, LIN H. Accurate image registration method for PCB defects detection[J]. The Journal of Engineering, 2018, 2018(16): 1662-1667. DOI: 10.1049/joe.2018.8272.

REN J C, JIANG J M, VLACHOS T. High-accuracy sub-pixel motion estimation from noisy images in Fourier domain[J]. IEEE Transactions on Image Processing, 2010, 19(5): 1379-1384. DOI: 10.1109/TIP.2009.2039056.

孙友涛, 孙轶, 花文波, 等. 基于AOI技术的PCB常见质量缺陷检测[J]. 科技风, 2020(8): 24. DOI: 10.19392/j.cnki.1671-7341.202008022. SUN Y T, SUN Y, HUA W B, et al. Common PCB quality defect detection based on AOI technology[J]. TechnologyWind, 2020(8): 24. DOI: 10.19392/j.cnki.1671-7341.202008022.

产叶林, 胡新平. 基于FAST和SURF的特征点快速匹配算法[J]. 计算机工程与设计, 2019, 40(12): 3500-3504. DOI: 10.16208/j.issn1000-7024.2019.12.023. CHAN Y L, HU X P. Fast featurepoint matching algorithm on FAST and SURF[J]. Computer Engineering and Design, 2019, 40(12): 3500-3504. DOI: 10.16208/j.issn1000-7024.2019.12.023.

TONG X H, YE Z, XU Y S, et al. Image registration with Fourier-based image correlation: a comprehensive review of developments and applications[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2019, 12(10): 4062-4081. DOI: 10.1109/JSTARS.2019.2937690.

HASSANIN A A T M, EL-SAMIE F E A, EL BANBY G M. A real-time approach for automatic defect detection from PCBs based on SURF features and morphological operations[J]. Multimedia Tools and Applications, 2019, 78(24): 34437-34457. DOI: 10.1007/s11042-019-08097-9.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

大模型发展综述：从BERT到Deepseek的技术演进

AlN/GaN混合缓冲层双异质结p-GaN HEMT直流特性仿真

超低功耗实时时钟电路的设计

一种基于特征上下文理解与切片分析的肺结核检测算法

面向处理器分支预测单元的Spectre攻击轻量化防御方法