Solder Paste Scooping Detection by Multilevel Visual Inspection of Printed Circuit Boards

被引：42

作者：

Benedek, Csaba ^{[1
,2
]}

Krammer, Oliver ^{[2
]}

Janoczki, Mihaly ^{[2
]}

Jakab, Laszlo ^{[2
]}

机构：

[1] Hungarian Acad Sci MTA SZTAKI, Distributed Events Anal Res Lab, Comp & Automat Res Inst, H-1111 Budapest, Hungary

[2] Budapest Univ Technol & Econ BME, Dept Elect Technol, H-1111 Budapest, Hungary

来源：

IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS | 2013年 / 60卷 / 06期

关键词：

Marked point process (MPP); printed circuit board (PCB); scooping; MARKED POINT PROCESS; PARAMETER-ESTIMATION; OBJECT EXTRACTION; SEGMENTATION;

D O I：

10.1109/TIE.2012.2193859

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

In this paper, we introduce an automated Bayesian visual inspection framework for printed circuit board (PCB) assemblies, which is able to simultaneously deal with various shaped circuit elements (CEs) on multiple scales. We propose a novel hierarchical multi-marked point process model for this purpose and demonstrate its efficiency on the task of solder paste scooping detection and scoop area estimation, which are important factors regarding the strength of the joints. A global optimization process attempts to find the optimal configuration of circuit entities, considering the observed image data, prior knowledge, and interactions between the neighboring CEs. The computational requirements are kept tractable by a data-driven stochastic entity generation scheme. The proposed method is evaluated on real PCB data sets containing 125 images with more than 10 000 splice entities.

引用

页码：2318 / 2331

页数：14

共 54 条

[1]

Bambos N., 1994, PROBAB ENG INFORM SC, V8, P229

[2] High-Speed Embedded-Object Analysis Using a Dual-Line Timed-Address-Event Temporal-Contrast Vision Sensor [J].

Belbachir, Ahmed Nabil ;

Hofstaetter, Michael ;

Litzenberger, Martin ;

Schoen, Peter .

IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, 2011, 58 (03) :770-783

[3]

Benedek C., 2011, 2011 18th IEEE International Conference on Image Processing (ICIP 2011), P2121, DOI 10.1109/ICIP.2011.6116029

[4] Building Development Monitoring in Multitemporal Remotely Sensed Image Pairs with Stochastic Birth-Death Dynamics [J].

Benedek, Csaba ;

Descombes, Xavier ;

Zerubia, Josiane .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2012, 34 (01) :33-50

[5] Detection of soldering defects in Printed Circuit Boards with Hierarchical Marked Point Processes [J].

Benedek, Csaba .

PATTERN RECOGNITION LETTERS, 2011, 32 (13) :1535-1543

[6] Detection of Object Motion Regions in Aerial Image Pairs With a Multilayer Markovian Model [J].

Benedek, Csaba ;

Sziranyi, Tamas ;

Kato, Zoltan ;

Zerubia, Josiane .

IEEE TRANSACTIONS ON IMAGE PROCESSING, 2009, 18 (10) :2303-2315

[7] An Adaptive Neural-Fuzzy Approach for Object Detection in Dynamic Backgrounds for Surveillance Systems [J].

Chacon-Murguia, Mario I. ;

Gonzalez-Duarte, Sergio .

IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, 2012, 59 (08) :3286-3298

[8]

Chatelain F, 2009, LECT NOTES COMPUT SC, V5681, P221, DOI 10.1007/978-3-642-03641-5_17

[9] A novel Fourier descriptor based image alignment algorithm for automatic optical inspection [J].

Chen, Chin-Sheng ;

Yeh, Chun-Wei ;

Yin, Peng-Yeng .

JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION, 2009, 20 (03) :178-189

[10] Optical PCB inspection system based on Hausdorff distance [J].

Chen, CJ ;

Lai, SH ;

Liu, SW ;

Ku, T ;

Yeh, SYC .

Machine Vision Applications in Industrial Inspection XIII, 2005, 5679 :53-61

← 1 2 3 4 5 6 →