Attention M-net for Automatic Pixel-Level Micro-crack Detection of Photovoltaic Module Cells in Electroluminescence Images

In the solar power industry, quality inspection of solar cells is a very important part of the production and application process. Micro-crack is a type of common defect that may be present in photovoltaic (PV) module cells which can reduce the power generation efficiency and service lifetime. However, it is difficult to identify micro-crack by the naked eye because it is readily confused with non-uniform backgrounds and complex textures in Electroluminescence (EL) images. In this paper, we propose Attention M-net which combines efficient segmentation model structure and attention mechanism. It is a novel micro-crack detection model for automated pixel-level micro-crack detection of PV module cells. The M-shaped structure solves "All Black" issue that is easy to occur due to the severe imbalance of the micro-crack segmentation dataset. And integration of attention mechanism into the network significantly improves the accuracy of segmentation. Because of the above two advantages, the proposed model can be accurately learned from a small annotated dataset, thereby saving the time of micro-crack EL images collection and pixel-level annotations. We extensively trained the proposed model on a small dataset of 20 annotated EL images which include 10 monocrystalline and 10 polycrystalline. The evaluated results on the test dataset demonstrate the high efficiency and accuracy of Attention M-net for pixel-level micro-crack detection of PV module cells in EL images.

[1]  Lucas J. van Vliet,et al.  Fully convolutional architecture vs sliding-window CNN for corneal endothelium cell segmentation , 2019, BMC biomedical engineering.

[2]  Chunhui Zhao,et al.  Multiclass Oblique Random Forests With Dual-Incremental Learning Capacity , 2020, IEEE Transactions on Neural Networks and Learning Systems.

[3]  Michael I. Jordan,et al.  Advances in Neural Information Processing Systems 30 , 1995 .

[4]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[5]  Yuanyuan Wu,et al.  Micro-cracks detection of multicrystalline solar cell surface based on self-learning features and low-rank matrix recovery , 2018, Sensor Review.

[6]  Quoc V. Le,et al.  Attention Augmented Convolutional Networks , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[7]  Allan Hanbury,et al.  Metrics for evaluating 3D medical image segmentation: analysis, selection, and tool , 2015, BMC Medical Imaging.

[8]  Minghai Yao,et al.  Improving the Efficiency of Encoder-Decoder Architecture for Pixel-Level Crack Detection , 2019, IEEE Access.

[9]  Aaron Carass,et al.  Why rankings of biomedical image analysis competitions should be interpreted with care , 2018, Nature Communications.

[10]  Dezso Sera,et al.  Automatic detection and evaluation of solar cell micro-cracks in electroluminescence images using matched filters , 2016, 2016 IEEE 43rd Photovoltaic Specialists Conference (PVSC).

[11]  Shuang Wang,et al.  Detection of Cracks in Electroluminescence Images by Fusing Deep Learning and Structural Decoupling , 2019, 2019 Chinese Automation Congress (CAC).

[12]  Bolei Zhou,et al.  Learning Deep Features for Discriminative Localization , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[13]  Julen Balzategui,et al.  Semi-automatic quality inspection of solar cell based on Convolutional Neural Networks , 2019, 2019 24th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA).

[14]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

[15]  Yu Jiang,et al.  A Machine Vision-based Realtime Anomaly Detection Method for Industrial Products Using Deep Learning , 2019, 2019 Chinese Automation Congress (CAC).

[16]  In-So Kweon,et al.  CBAM: Convolutional Block Attention Module , 2018, ECCV.

[17]  Amit Kumar Garg,et al.  A Mamdani Fuzzy Logic System to Enhance Solar Cell Micro-Cracks Image Processing , 2018, 3D Research.

[18]  Kaige Zhang,et al.  CrackGAN: A Labor-Light Crack Detection Approach Using Industrial Pavement Images Based on Generative Adversarial Learning , 2019, ArXiv.

[19]  Kun Liu,et al.  Solar cell surface defect inspection based on multispectral convolutional neural network , 2018, Journal of Intelligent Manufacturing.

[20]  Christoph J. Brabec,et al.  A Benchmark for Visual Identification of Defective Solar Cells in Electroluminescence Imagery , 2018 .

[21]  Jun Fu,et al.  Dual Attention Network for Scene Segmentation , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[22]  Raghav Mehta,et al.  M-net: A Convolutional Neural Network for deep brain structure segmentation , 2017, 2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017).

[23]  Enhua Wu,et al.  Squeeze-and-Excitation Networks , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[24]  In-line photoluminescence imaging of crystalline silicon solar cells for micro-crack detection , 2016, 2016 IEEE International Conference on Imaging Systems and Techniques (IST).