期刊
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
卷 19, 期 6, 页码 7335-7345出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TII.2022.3211088
关键词
Photovoltaic cells; Feature extraction; Convolutional neural networks; Silicon; Neural networks; Visualization; Support vector machines; Attention; automatic defect detection; electroluminescence image; saliency; solar cell
In this article, a global pairwise similarity and concatenated saliency guided neural network is proposed for automatically detecting defects in solar cells using electroluminescence images. The proposed method significantly outperforms baseline models and demonstrates the effectiveness of the global similarity module and the concatenated saliency module in defect detection.
Electroluminescence imaging becomes a very useful technique to automatically detect defects for solar cells since it can provide high resolution electroluminescence images. However, few methods explicitly consider the visual characteristics of the defects and the noises in solar cells. In this article, a global pairwise similarity and concatenated saliency guided neural network is proposed by fully considering the observed visual characteristics in electroluminescence solar cell images. The proposed network exploits a global pairwise similarity module and a concatenated saliency module to refine the features extracted by the convolutional neural network. The global pairwise similarity module aims to refine the features of an image pixel by modeling long-range dependencies. The concatenated saliency module is exploited to suppress the background and decouple different salient regions to better represent the features of an image. Extensive experiments based on five different baselines, i.e., VGG16, ResNet56, ResNet50, DenseNet40, and GoogleNet, prove that the proposed method significantly outperforms the baseline models and show that both the global similarity module and the concatenated saliency module can help detect defective solar cells in electroluminescence images.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据