journal article·2023-08Open access

Deep learning method for enhancing luminescence image resolution

Priya Dwivedi, Juergen W. Weber, Robert Lee Chin, Thorsten Trupke, Ziv Hameiri

Abstract

Luminescence imaging is a fast and non-destructive method to spatially resolve non-uniform electrical properties of solar cells. The spatial resolution of these images determines the smallest identifiable features. The higher the spatial resolution of an image, the better the capability to detect small defects. However, high-resolution cameras with high near-infrared light sensitivity that are suited to luminescence imaging of crystalline silicon are often expensive. In this study, we present a method, based on deep learning, that enhances the spatial resolution of luminescence images computationally with minimal cost. We also demonstrate the ability to overcome noise which is inevitable in any imaging system. This approach provides a simple and promising path toward reducing the cost of luminescence imaging systems and enhancing the capability of existing systems.
Source: openalex_inverted_index · Quality: baseline

Research context

OpenAlex topics: Advanced Image Processing Techniques · CCD and CMOS Imaging Sensors · Advanced Fluorescence Microscopy Techniques

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

References (51)

Show source-provided references
1. The underestimated potential of solar energy to mitigate climate change10.1038/nenergy.2017.140 ↗
2. Commercial progress and challenges for photovoltaics10.1038/nenergy.2015.15 ↗
3. Economically sustainable scaling of photovoltaics to meet climate targets10.1039/C6EE00484A ↗
4. Photographic surveying of minority carrier diffusion length in polycrystalline silicon solar cells by electroluminescence10.1063/1.1978979 ↗
5. Photoluminescence imaging of silicon wafers10.1063/1.2234747 ↗
6. Photoluminescence imaging for photovoltaic applications10.1016/j.egypro.2012.02.016 ↗
7. 2019
8. Solar cells micro crack detection technique using state-of-the-art electroluminescence imaging
9. Inspection and condition monitoring of large-scale photovoltaic power plants: a review of imaging technologies10.1016/j.rser.2022.112353 ↗
10. Super-resolution: a comprehensive survey10.1007/s00138-014-0623-4 ↗
11. Super-resolution image reconstruction: a technical overview10.1109/MSP.2003.1203207 ↗
12. Super-resolution reconstruction and its future research direction
13. 2017
14. Super-resolution mosaicking of UAV surveillance video
15. Robust super-resolution volume reconstruction from slice acquisitions: application to fetal brain MRI10.1109/TMI.2010.2051680 ↗
16. A computationally efficient super-resolution algorithm for video processing using partition filters10.1109/TCSVT.2007.893833 ↗
17. A super-resolution reconstruction algorithm for hyperspectral images10.1016/j.sigpro.2012.01.020 ↗
18. Multiframe super-resolution employing a spatially weighted total variation model10.1109/TCSVT.2011.2163447 ↗
19. Deep learning for image super-resolution: a survey10.1109/TPAMI.2020.2982166 ↗
20. Cubic convolution interpolation for digital image processing10.1109/TASSP.1981.1163711 ↗
21. Lanczos filtering in one and two dimensions10.1175/1520-0450(1979)018<1016:LFIOAT>2.0.CO;2 ↗
22. Wang · 2018
23. Image super-resolution using deep convolutional networks10.1109/TPAMI.2015.2439281 ↗
24. EnhanceNet: single image super-resolution through automated texture synthesis
25. MemNet: a persistent memory network for image restoration
26. Super-resolution from a single image
27. Single-image super-resolution using sparse regression and natural image prior10.1109/TPAMI.2010.25 ↗
28. Image super-resolution using gradient profile prior
29. Accelerating the super-resolution convolutional neural network
30. Accurate image super-resolution using very deep convolutional networks
31. Deeply-recursive convolutional network for image super-resolution
32. Photo-realistic single image super-resolution using a generative adversarial network
33. Image super-resolution via deep recursive residual network
34. Residual dense network for image super-resolution
35. Generative adversarial networks10.1145/3422622 ↗
36. Jolicoeur-Martineau · 2018
37. Super-resolution reconstruction of turbulent velocity fields using a generative adversarial network-based artificial intelligence framework10.1063/1.5127031 ↗
38. A lightweight image super-resolution network based on ESRGAN for rapid tomato leaf disease classification
39. 3D brain MRI reconstruction based on 2D super-resolution technology
40. Super-resolution of sea surface temperature with convolutional neural network-and generative adversarial network-based methods10.2166/wcc.2022.291 ↗
41. Small-object detection in remote sensing images with end-to-end edge-enhanced GAN and object detector network10.3390/rs12091432 ↗
42. A deep learning approach to increase luminescence image resolution of solar cells
43. Über spontane stromschwankungen in verschiedenen elektrizitätsleitern10.1002/andp.19183622304 ↗
44. Modern image quality assessment10.1007/978-3-031-02238-8 ↗
45. The unreasonable effectiveness of deep features as a perceptual metric
46. Simonyan · 2015
47. ImageNet classification with deep convolutional neural networks
48. Iandola · 2016
49. The 2018 PIRM challenge on perceptual image super-resolution
50. Zafirovska · 2019
51. A deep learning approach to denoise electroluminescence images of solar cells