Using Deep Attention Networks to Extract Defects in Crisscross Background

Chen Tao Hsu, Yi Shan Lee, Jen Hui Chuang

研究成果: Conference contribution同行評審

摘要

Nowadays, automatic optical inspection (AOI) has been widely used in advanced manufactory. In AOI area, crisscross background may influence extraction of defect features. A package, semi-finished product of textile industry, usually has cricross background. This study aims to classify four types of package defects, which are wound-in waste, spillover, cobwebs, and dirt. We use a well-known supervised attention-neural-network architecture to classify the four types of package defects effectively. In this study, we use three steps to decide the best strategies. First, we find the best location of channel attention blocks for the deep attention network. After that, we compare two image preprocessing methods to enhance the features of defect. To understand if regularize the background trend will improve the performance or not, we create two kinds of dataset, rotated and non-rotated. Our study improves traditional AOI methods. The experimental results show that the proposed procedures can extract the package defects with interlacing background efficiently.

原文English
主出版物標題Proceedings - 2020 International Conference on Pervasive Artificial Intelligence, ICPAI 2020
發行者Institute of Electrical and Electronics Engineers Inc.
頁面246-252
頁數7
ISBN(電子)9781665404839
DOIs
出版狀態Published - 12月 2020
事件1st International Conference on Pervasive Artificial Intelligence, ICPAI 2020 - Taipei, Taiwan
持續時間: 3 12月 20205 12月 2020

出版系列

名字Proceedings - 2020 International Conference on Pervasive Artificial Intelligence, ICPAI 2020

Conference

Conference1st International Conference on Pervasive Artificial Intelligence, ICPAI 2020
國家/地區Taiwan
城市Taipei
期間3/12/205/12/20

指紋

深入研究「Using Deep Attention Networks to Extract Defects in Crisscross Background」主題。共同形成了獨特的指紋。

引用此