Low-cost smartphone-based LIBS combined with deep learning image processing for accurate lithology recognition
| Autor: | Mengfan Wu, Yixiang Duan, Xu Wang, Zhongjun Zhao, Ruiqin Zheng, Zhuo Liu, Sha Chen |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Computer science
Lithology Image processing 02 engineering and technology 01 natural sciences Catalysis law.invention Deep Learning law Image Processing Computer-Assisted Materials Chemistry Computer vision Coupling Spectrometer business.industry Spectrum Analysis Deep learning 010401 analytical chemistry Detector Metals and Alloys Equipment Design General Chemistry 021001 nanoscience & nanotechnology Laser 0104 chemical sciences Surfaces Coatings and Films Electronic Optical and Magnetic Materials CMOS Ceramics and Composites Smartphone Artificial intelligence 0210 nano-technology business Algorithms |
| Zdroj: | Chemical Communications. |
| ISSN: | 1364-548X 1359-7345 |
| Popis: | A low-cost and multi-channel smartphone-based spectrometer was developed for LIBS. As the CMOS detector is two-dimensional, simultaneous multichannel detection was achieved by coupling a linear array of fibres for light collection. Thus, besides the atomic information, the spectral images containing the propagation and spatial distribution characters of a laser induced plasma plume could be recorded. With these additional features, accurate rock type prediction was achieved by processing the raw data directly through a deep learning model. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|