Comparative Analysis of Hyperspectral Image Reconstruction Using Deep Learning for Agricultural and Biological Applications

TL;DR

This paper compares deep learning methods for reconstructing hyperspectral images from RGB data to enable cost-effective quality assessment in agriculture, highlighting HRNET's superior performance and the potential of AI-driven reconstruction.

Contribution

It introduces a comparative analysis of multiple deep learning algorithms for hyperspectral reconstruction from RGB images in agricultural applications, emphasizing HRNET's effectiveness.

Findings

HRNET achieved the lowest MRAE of 0.07 and RMSE of 0.03.

Reconstructed images showed high spectral and visual quality compared to ground truth.

Deep learning-based reconstruction offers a promising, cost-effective tool for agricultural quality assessment.

Abstract

Hyperspectral imaging (HSI) has become a key technology for non-invasive quality evaluation in various fields, offering detailed insights through spatial and spectral data. Despite its efficacy, the complexity and high cost of HSI systems have hindered their widespread adoption. This study addressed these challenges by exploring deep learning-based hyperspectral image reconstruction from RGB (Red, Green, Blue) images, particularly for agricultural products. Specifically, different hyperspectral reconstruction algorithms, such as Hyperspectral Convolutional Neural Network - Dense (HSCNN-D), High-Resolution Network (HRNET), and Multi-Scale Transformer Plus Plus (MST++), were compared to assess the dry matter content of sweet potatoes. Among the tested reconstruction methods, HRNET demonstrated superior performance, achieving the lowest mean relative absolute error (MRAE) of 0.07, root mean square error (RMSE) of 0.03, and the highest peak signal-to-noise ratio (PSNR) of 32.28 decibels (dB). Some key features were selected using the genetic algorithm (GA), and their importance was interpreted using explainable artificial intelligence (XAI). Partial least squares regression (PLSR) models were developed using the RGB, reconstructed, and ground truth (GT) data. The visual and spectra quality of these reconstructed methods was compared with GT data, and predicted maps were generated. The results revealed the prospect of deep learning-based hyperspectral image reconstruction as a cost-effective and efficient quality assessment tool for agricultural and biological applications.