Open AccessCapacitor Detection on PCB Using AdaBoost Classifier
Author(s) -
Jian Fang,
Lei Shang,
Guangchun Gao,
Kai Xiong,
Cui Zhang
Publication year - 2020
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1631/1/012185
Subject(s) - capacitor , adaboost , artificial intelligence , classifier (uml) , computer science , pattern recognition (psychology) , boosting (machine learning) , feature extraction , computer vision , engineering , voltage , electrical engineering
In PCB manufacturing, automatic optical inspection (AOI) is a key technology to improve production efficiency and quality. At present, most of the AOI algorithms are aimed at PCB and SMD components. An AOI algorithm for plug-in polar capacitors is proposed in this paper. The algorithm mainly uses AdaBoost classifier based on Haar-like feature to realize the recognition of plug-in capacitors. The polarity of the capacitor is detected by comparing the image features of the target capacitor. Experimental results show that the algorithm proposed in this paper can effectively detect two kinds of defects: capacitor missing and capacitor polarity opposite. The algorithm can be applied to the AOI detection of PCB before and after wave soldering.