A PCB Dataset for Defects Detection and Classification

TL;DR

This paper introduces a new synthesized PCB dataset with 1386 images for defect detection and classification, and proposes a reference-based method using an end-to-end neural network that outperforms traditional pixel-wise approaches.

Contribution

The paper provides a publicly available PCB defect dataset and develops a novel reference-based neural network approach for defect detection and classification.

Findings

The dataset contains 1386 images with 6 defect types.

The proposed method outperforms conventional pixel-by-pixel techniques.

End-to-end neural network achieves superior accuracy in defect classification.

Abstract

To coupe with the difficulties in the process of inspection and classification of defects in Printed Circuit Board (PCB), other researchers have proposed many methods. However, few of them published their dataset before, which hindered the introduction and comparison of new methods. In this paper, we published a synthesized PCB dataset containing 1386 images with 6 kinds of defects for the use of detection, classification and registration tasks. Besides, we proposed a reference based method to inspect and trained an end-to-end convolutional neural network to classify the defects. Unlike conventional approaches that require pixel-by-pixel processing, our method firstly locate the defects and then classify them by neural networks, which shows superior performance on our dataset.