Deep Coding Patterns Design for Compressive Near-Infrared Spectral Classification
This work addresses the challenge of costly near-infrared spectral sensing for researchers in imaging and compression, though it is incremental as it builds on existing compressive domain classification methods.
The paper tackles the problem of improving spectral classification accuracy in compressive spectral imaging by jointly designing coding patterns and network parameters, achieving up to a 10% increase in classification accuracy compared to traditional methods.
Compressive spectral imaging (CSI) has emerged as an attractive compression and sensing technique, primarily to sense spectral regions where traditional systems result in highly costly such as in the near-infrared spectrum. Recently, it has been shown that spectral classification can be performed directly in the compressive domain, considering the amount of spectral information embedded in the measurements, skipping the reconstruction step. Consequently, the classification quality directly depends on the set of coding patterns employed in the sensing step. Therefore, this work proposes an end-to-end approach to jointly design the coding patterns used in CSI and the network parameters to perform spectral classification directly from the embedded near-infrared compressive measurements. Extensive simulation on the three-dimensional coded aperture snapshot spectral imaging (3D-CASSI) system validates that the proposed design outperforms traditional and random design in up to 10% of classification accuracy.