A5050070928- Optical Polarization and Ellipsometry
- Photonic and Optical Devices
- Advanced Chemical Sensor Technologies
- Remote-Sensing Image Classification
- Sparse and Compressive Sensing Techniques
- Random lasers and scattering media
- Spectroscopy and Chemometric Analyses
- Photonic Crystals and Applications
- Optical Coherence Tomography Applications
- Smart Agriculture and AI
Shandong University
2023-2024
Computational spectrometers have great application prospects in hyperspectral detection, and fast high-precision situ measurement is an important development trend. The computational spectrometer based on iterative algorithms has low requirements for resources easy to achieve hardware integration measurement. However, are difficult high reconstruction accuracy due the ill-posed nature of problems. Neural networks powerful learning capabilities can spectral reconstruction. solely relying...
A computational spectrometer is a novel form of powerful for portable in situ applications. In the encoding part spectrometer, filters with highly non-correlated properties are requisite compressed sensing, which poses severe challenges optical design and fabrication. reconstruction conventional iterative algorithms featured limited efficiency accuracy, hinders their application real-time measurements. This study proposes neural network trained by small dataset high-correlation filters. We...
Computational spectrometer is powerful for portable in situ applications. To achieve better signal to noise ratio (SNR), broadband optical filters are more commonly introduced. As conventional sparse signals reconstruction algorithms like gradient projection, its performance relies on the low correlation property of filters, which poses severe challenge design and fabrication. In this study, we propose a lightweight neural network(NN) named HBOF-Net that can be compatible with...