Reconstruction-Assisted Band Selection for Non-Destructive Prediction of Citrus Soluble Solids Content from VNIR Hyperspectral Images
Open Access
Abstract
The increasing demand for better fruit flavor and eating quality has driven the need for rapid and non-destructive assessment of internal attributes to support fruit grading and precision supply. Visible–near-infrared hyperspectral imaging (VNIR-HSI) provides rich spectral–spatial information for evaluating sweetness in citrus fruit, but its practical use is constrained by high spectral dimensionality, redundancy, and system cost. Here, we propose a reconstruction-assisted, attention-guided band-selection framework for non-destructive prediction of soluble solids content (SSC) in Shimen honey mandarins. The framework integrates spectral–spatial attention, probability-based differentiable band selection, and full-band reconstruction into a unified end-to-end architecture, enabling compact and informative band learning. Using 952 samples, the model selected 56 informative bands from the original 176-band hyperspectral data and achieved competitive SSC prediction on the test set (RMSE = 0.63 °Brix, R2 = 0.80) while maintaining high-fidelity reconstruction of the full-band hyperspectral cube from the compact input (peak signal-to-noise ratio, PSNR = 36.47 dB; structural similarity index, SSIM = 0.89). These findings support the proposed framework as a methodological proof of concept for non-destructive citrus quality evaluation, indicating that substantial spectral compression can be achieved under the current VNIR setting while largely preserving predictive performance. The selected bands may provide candidate spectral regions for future compact citrus-quality sensing systems.Keywords
Funding Information
- Ministry of Science and Technology of the People's Republic of China (2023YFD2100300)
- Department of Science and Technology of Hunan Province (2024RC3075)
This publication has 41 references indexed in Scilit:
- Convolutional neural networks fusing spectral shape features with attentional mechanisms for accurate prediction of soluble solids content in applesJournal of Food Measurement and Characterization, 2024
- Nondestructive determining the soluble solids content of citrus using near infrared transmittance technology combined with the variable selection algorithmArtificial Intelligence in Agriculture, 2020
- CBAM: Convolutional Block Attention Module2018
- Effect of spectrum measurement position variation on the robustness of NIR spectroscopy models for soluble solids content of appleBiosystems Engineering, 2016
- Improvement on enhanced Monte-Carlo outlier detection methodChemometrics and Intelligent Laboratory Systems, 2016
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- NIR Spectroscopy Applications for Internal and External Quality Analysis of Citrus Fruit—A ReviewFood and Bioprocess Technology, 2011
- Nondestructive measurement of internal quality of Nanfeng mandarin fruit by charge coupled device near infrared spectroscopyComputers and Electronics in Agriculture, 2010
- Key wavelengths screening using competitive adaptive reweighted sampling method for multivariate calibrationAnalytica Chimica Acta, 2009
- The spectral image processing system (SIPS)—interactive visualization and analysis of imaging spectrometer dataRemote Sensing of Environment, 1993