Applied Nanophotonics, Liquid Crystals and Biomedical Optics

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.