.png){kind=icon}
返回
Effective Defect Detection Method Based on Bilinear Texture Features for LGPs
.png){kind=icon}
OA
AI
DOI：10.1109/ACCESS.2021.3111410.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Automatic defect detection of light guide plates (LGPs) is an important task in the manufacture of liquid crystal displays. During thermo-printing, defects of tag lines on LGPs may occur easily, and these defects are of two categories: bubbles and missing tag lines. These defects lack salient visual attributes, such as edge-based and region-based features, and as such, traditional methods fail to detect them. To address this, we propose a Dense-bilinear convolutional neural network (BCNN), an end-to-end defect detection network, utilizing Dense-blocks (Huang et al., 2017), Bilinear feature layers (Lin et al., 2015), and squeeze-and-excitation blocks (Hu et al., 2018). Our network exploits fine-grained texture features, which leads to parameter reduction and accuracy enhancement. We validate our network on our LGP dataset containing 5,860 images from three cases: bubbles, tag line existence, and tag line missing. Our network outperforms AlexNet (Krizhevsky et al., 2012), VGG (Simonyan and Zisserman, 2014) and ResNet (He et al., 2016), on both the public and our LGP datasets with less GPU memory consumption.
Keyword:
Feature extraction
Image edge detection
Convolutional neural networks
Task analysis
Graphics processing units
Object segmentation
Neural networks
Defects detection
texture classification
bilinear convolutional neural networks
期刊
IF:
3.6
论文数:
9.8W
被引数:
29.4W
机构
引用论文
Nanocrystalline silicon films as multifunctional material for optoelectronic and photovoltaic applications纳米硅薄膜作为光电和光伏应用的多功能材料
PREAI
分享收藏
Structural study of lanthanides(III) in aqueous nitrate and chloride solutions by EXAFS通过EXAFS对硝酸盐和氯化物水溶液中镧系元素 (III) 的结构研究
PREAI
分享收藏Approches familiales des troubles du comportement alimentaire de l'enfant et de l'adolescent.png)
IF0
PREAI
分享收藏分享收藏Design of deep convolutional neural network architectures for automated feature extraction in industrial inspection面向工业检测自动特征提取的深度卷积神经网络架构设计
PREAI
分享收藏
查看更多内容