Capacitor Detection in PCB Using YOLO Algorithm

Optical inspection is an important task of PCB manufacturing. Once PCB manufactured in small batch production, it needs a fast way to teach and adjust the automatic optical inspection (AOI) system for the inspection of the batch of product. This paper proposes a capacitor detection method based on YOLO algorithm for printed circuit board (PCB) assembly. YOLO is a kind of fast object detection method based on convolutional neural network (CNN). The deep network architecture of CNN can detect discrimination features from all of the input images, so we do not need experts to define image features. To verify the effectiveness of the proposed approach, samples of PCB images with nine kinds of capacitors are collected and trained by YOLO. Experimental results show all the types of capacitors in PCB can be detected and the average detection time is less than 0.3 second. The detection time is fast enough to develop an on-line PCB assembly inspection.

[1]  T. J. Mateo Sanguino,et al.  Computer-aided system for defect inspection in the PCB manufacturing process , 2012, 2012 IEEE 16th International Conference on Intelligent Engineering Systems (INES).

[2]  P S Malge,et al.  PCB Defect Detection, Classification and Localization using Mathematical Morphology and Image Processing Tools , 2014 .

[3]  Laszlo Jakab,et al.  Automatic Optical Inspection of Soldering , 2013 .

[4]  Giuseppe Acciani,et al.  Application of neural networks in optical inspection and classification of solder joints in surface mount technology , 2006, IEEE Transactions on Industrial Informatics.

[5]  Derek C. Rose,et al.  Deep Machine Learning - A New Frontier in Artificial Intelligence Research [Research Frontier] , 2010, IEEE Computational Intelligence Magazine.

[6]  Trevor Darrell,et al.  Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation , 2013, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[7]  Xie Hongwei,et al.  Solder joint inspection based on neural network combined with genetic algorithm , 2013 .

[8]  T. S. Yun,et al.  Support vector machine-based inspection of solder joints using circular illumination , 2000 .

[9]  Ross B. Girshick,et al.  Fast R-CNN , 2015, 1504.08083.

[10]  Ali Farhadi,et al.  YOLO9000: Better, Faster, Stronger , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[11]  Young Shik Moon,et al.  Visual inspection system for the classification of solder joints , 1999, Pattern Recognit..

[12]  Yun Zhang,et al.  ANN Ensembles Based Machine Vision Inspection for Solder Joints , 2007, 2007 IEEE International Conference on Control and Automation.

[13]  Jae-Hoon Kim,et al.  Neural network-based inspection of solder joints using a circular illumination , 1995, Image Vis. Comput..

[14]  Andrew L. Maas.  Rectifier Nonlinearities Improve Neural Network Acoustic Models , 2013 .

[15]  Rob Fergus,et al.  Visualizing and Understanding Convolutional Networks , 2013, ECCV.

[16]  Wei Liu,et al.  SSD: Single Shot MultiBox Detector , 2015, ECCV.

[17]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[18]  Zahurin Samad,et al.  Solder joint inspection with multi-angle imaging and an artificial neural network , 2008 .

[19]  Cihan H. Dagli,et al.  Automatic PCB Inspection Algorithms: A Survey , 1996, Comput. Vis. Image Underst..

[20]  Luc Van Gool,et al.  The Pascal Visual Object Classes (VOC) Challenge , 2010, International Journal of Computer Vision.

[21]  Detlef Streitferdt,et al.  On the development of intelligent optical inspections , 2017, 2017 IEEE 7th Annual Computing and Communication Workshop and Conference (CCWC).

[22]  Nima Tajbakhsh,et al.  Convolutional Neural Networks for Medical Image Analysis: Full Training or Fine Tuning? , 2016, IEEE Transactions on Medical Imaging.

[23]  Ali Farhadi,et al.  You Only Look Once: Unified, Real-Time Object Detection , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[24]  Yu Wang,et al.  Microfocus X-ray printed circuit board inspection system , 2014 .

[25]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[26]  Yee Whye Teh,et al.  A Fast Learning Algorithm for Deep Belief Nets , 2006, Neural Computation.

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