A REAL-TIME SYSTEM FOR PCB AUTOMATED INSPECTION USING CONVOLUTIONAL NEURAL NETWORK

Abstract

The paper presents the application of image processing technology in
checking real-time electronic components on the Printed Circuit Board (PCB). The
convolutional neural network model is used to extract features and predict of
objects in a new image. The PCB system has a working capacity of 120
products/hour. From the experiment, it is certain that the proposed system has
an accuracy of up to 96% for PCB. The various noise effects from the environment
are considered to evaluate the effectiveness of the system such as brightness,
image size, and background.