FICS-PCB: A Multi-Modal Image Dataset for Automated Printed Circuit Board Visual Inspection

Over the years, the computer vision and machine learning disciplines have considerably advanced the field of automated visual inspection for Printed Circuit Board (PCB) assurance. However, in practice, the capabilities and limitations of these advancements remain unknown because there are few publicly accessible datasets for PCB visual inspection and even fewer that contain images that simulate realistic application scenarios. To address this need, we propose a publicly available dataset, FICS-PCB , to facilitate the development of robust methods for automated PCB visual inspection. The proposed dataset includes challenging cases from four variable aspects: PCB manufacturing, illumination, scale, and image sensor. The FICS-PCB dataset consists of 8,685 images of 31 PCB samples and contains 75,965 annotated components. This paper reviews the existing datasets and methodologies used for PCB visual inspection, discusses problem challenges, describes the proposed dataset, and presents baseline performances using feature-based and deep learning methods for automated PCB component visual inspection.

[1]  Huihui. Wu,et al.  Automated visual inspection of surface mounted chip components , 2010, 2010 IEEE International Conference on Mechatronics and Automation.

[2]  Tae-Hyoung Park,et al.  SMD Classification for Automated Optical Inspection Machine Using Convolution Neural Network , 2019, International Conference on Robotic Computing.

[3]  Martin Kampel,et al.  A dataset for computer-vision-based PCB analysis , 2015, 2015 14th IAPR International Conference on Machine Vision Applications (MVA).

[4]  Karl Ricanek,et al.  PCB-METAL: A PCB Image Dataset for Advanced Computer Vision Machine Learning Component Analysis , 2019, 2019 16th International Conference on Machine Vision Applications (MVA).

[5]  Feng Xie,et al.  Detecting PCB component placement defects by genetic programming , 2013, 2013 IEEE Congress on Evolutionary Computation.

[6]  E. Guerra,et al.  A three-dimensional automated visual inspection system for SMT assembly , 2001 .

[7]  Farinaz Koushanfar,et al.  A Survey of Hardware Trojan Taxonomy and Detection , 2010, IEEE Design & Test of Computers.

[8]  Peng Wei,et al.  A PCB Dataset for Defects Detection and Classification , 2019, ArXiv.

[9]  Wen-Yen Wu,et al.  Automated inspection of printed circuit boards through machine vision , 1996 .

[10]  SeungGeun Youn,et al.  Automatic classification of SMD packages using neural network , 2014, 2014 IEEE/SICE International Symposium on System Integration.

[11]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[12]  Sharat Chandra Bhardwaj,et al.  Detection of Bare PCB Defects by Image Subtraction Method using Machine Vision , 2011 .

[13]  David J. Crandall,et al.  Deep Neural Network–Based Detection and Verification of Microelectronic Images , 2020, J. Hardw. Syst. Secur..

[14]  Alan Crispin,et al.  Automated inspection of PCB components using a genetic algorithm template-matching approach , 2007 .

[15]  Sergey Ioffe,et al.  Rethinking the Inception Architecture for Computer Vision , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[16]  Mohit Borthakur,et al.  A Comparative Study of Automated PCB Defect Detection Algorithms and to Propose an Optimal Approach to Improve the Technique , 2015 .

[17]  Tae-Hyoung Park,et al.  Wavelet Transform Based Image Template Matching for Automatic Component Inspection , 2009 .

[18]  Abhishek Dutta,et al.  The VIA Annotation Software for Images, Audio and Video , 2019, ACM Multimedia.

[19]  Marcelo R. Stemmer,et al.  Inspecting surface mounted devices using k nearest neighbor and Multilayer Perceptron , 2015, 2015 IEEE 24th International Symposium on Industrial Electronics (ISIE).

[20]  Marcelo Ricardo Stemmer,et al.  Automated PCB inspection in small series production based on SIFT algorithm , 2015, 2015 IEEE 24th International Symposium on Industrial Electronics (ISIE).

[21]  Weisi Lin,et al.  Saliency-Based Defect Detection in Industrial Images by Using Phase Spectrum , 2014, IEEE Transactions on Industrial Informatics.

[22]  Hui-Hui Wu,et al.  A visual inspection system for surface mounted components based on color features , 2009, 2009 International Conference on Information and Automation.

[23]  S. A. Chavan,et al.  Automatic PCB Defects Detection and Classification using Matlab , 2014 .

[24]  Li Fei-Fei,et al.  ImageNet: A large-scale hierarchical image database , 2009, CVPR.

[25]  Shang-Hong Lai,et al.  A Flexible PCB Inspection System Based on Statistical Learning , 2012, J. Signal Process. Syst..

[26]  Neelum Dave,et al.  PCB Defect Detection Using Image Processing And Embedded System , 2016 .

[27]  Abhishek Dutta,et al.  The VGG Image Annotator (VIA) , 2019, ArXiv.

[28]  Paolo Napoletano,et al.  Benchmark Analysis of Representative Deep Neural Network Architectures , 2018, IEEE Access.

[29]  Jie Yang,et al.  Online PCB Defect Detector On A New PCB Defect Dataset , 2019, ArXiv.

[30]  K. Sundaraj,et al.  PCB inspection for missing or misaligned components using background subtraction , 2009 .