Conversion of RGB Camera into Hyperspectral Imager Using a Liquid Crystal Spectral Modulator and Artificial Intelligence
Source abstract
Abstract
High Resolution Image Download MS PowerPoint Slide Hyperspectral imaging extracts spectral information for quantitative material identification, yet its adoption remains constrained by dispersive optics, filter arrays, and mechanically scanned architectures. Here, we introduce a method for converting a standard RGB or color-masked sensor into a hyperspectral imager through programmable photonic encoding and physics-aware neural inversion. A single electrically tunable liquid-crystal (LC) spectral modulator, operating via voltage-controlled birefringent interference, dynamically reshapes incident spectra to generate a sequence of structured spectral mixing states. This reconfigurable encoding lifts the intrinsic three-channel limitation of conventional sensors, without modifying the detector or introducing dispersive elements. The inherent spectral decomposition of the color channels significantly reduces the dimensionality and complexity of the inverse problem. The captured multiplexed data are modeled as a conditioned inverse problem governed by the spectral transfer functions of the modulator and sensor. To recover narrowband spectral components, a wavelength-resolved artificial neural network array (ANNA) is implemented that performs band-specific inversion, optimizing information fusion according to the spectral sensitivity and encoding matrix. This optical-digital codesign enhances spectral identifiability and stability while preserving hardware simplicity. Accurate visible-near-infrared range hyperspectral reconstruction is demonstrated experimentally and validates material sensitivity by quantifying olive oil adulteration in canola oil mixtures, resolving subtle absorption variations indistinguishable in RGB space. By redefining color cameras as programmable spectral measurement systems, this work establishes a compact, scalable pathway toward deployable hyperspectral imaging and illustrates how structured photonic modulation and ANNA can fundamentally extend the information capacity of conventional imaging platforms.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Neural Networks and Reservoir Computing · Photonic Crystals and Applications · Optical Polarization and Ellipsometry
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Electro-optics and Photonics Engineering and the Ilse Katz Institute of Nanoscale Science and Technology, ECE-School
Ben Gurion University of the Negev
Department of Electrical Engineering and Physics
Sami Shamoon College of Engineering
Funding
Ministry of Innovation, Science and Technology
References (26)
Show source-provided references
1. 10.1186/s43014-024-00246-410.1186/s43014-024-00246-4 ↗
2. 10.3390/electronics1423457510.3390/electronics14234575 ↗
3. 10.1021/acs.jafc.4c0868010.1021/acs.jafc.4c08680 ↗
4. 10.1016/j.pdpdt.2025.10464510.1016/j.pdpdt.2025.104645 ↗
5. 10.3390/technologies1305017010.3390/technologies13050170 ↗
6. 10.1016/j.compag.2024.10903710.1016/j.compag.2024.109037 ↗
7. 10.1002/advs.20240444810.1002/advs.202404448 ↗
8. 10.1038/s41377-022-00743-610.1038/s41377-022-00743-6 ↗
9. 10.1364/OPTICA.6.00092110.1364/OPTICA.6.000921 ↗
10. 10.1109/TIP.2018.288407610.1109/TIP.2018.2884076 ↗
11. 10.1145/2661229.266126210.1145/2661229.2661262 ↗
12. 10.1364/JOSAA.32.00175410.1364/JOSAA.32.001754 ↗
13. 10.1364/OE.15.01401310.1364/OE.15.014013 ↗
14. 10.1109/TGRS.2021.310039310.1109/TGRS.2021.3100393 ↗
15. Miao, X.; Yuan, X.; Pu, Y.; Athitsos, V. lambda-Net: Reconstruct Hyperspectral Images From a Snapshot Measurement. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) , 2019.10.1109/ICCV.2019.00416 ↗
16. Wang, L.; Sun, C.; Zhang, M.; Fu, Y.; Huang, H. DNU : Deep Non-Local Unrolling for Computational Spectral Imaging. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , 2020.10.1109/CVPR42600.2020.00173 ↗
17. 10.1364/OE.52573210.1364/OE.525732 ↗
18. 10.1049/htl2.1209810.1049/htl2.12098 ↗
19. 10.3390/s2411366610.3390/s24113666 ↗
20. Yang D. · 201410.1002/9781118751992 ↗
21. 10.1364/OE.50815010.1364/OE.508150 ↗
22. 10.1364/OE.21.00177910.1364/OE.21.001779 ↗
23. 10.3390/ma1419554010.3390/ma14195540 ↗
24. 10.1021/acsphotonics.4c0191610.1021/acsphotonics.4c01916 ↗
25. 10.1002/lpor.20220091310.1002/lpor.202200913 ↗
26. 10.1002/lpor.20250054710.1002/lpor.202500547 ↗