Adaptive RGB–VNIR spectral fusion for non-destructive quality assessment of Canadian wild rice kernels
- 1The Tourism College of Changchun University, College of Artificial Intelligence , ,
Abstract
Introduction: Canadian wild rice kernels exhibit diverse postharvest variations, including breakage, discoloration, insect damage, and incomplete dehulling, making accurate and non-destructive classification important for screening and grading. However, RGB imaging may be insufficient for distinguishing kernels with subtle or overlapping visual characteristics, while visible–near-infrared (VNIR) spectra provide complementary information but contain substantial redundancies. Moreover, conventional multimodal fusion strategies based on direct concatenation or fixed weighting cannot readily adapt to sample-specific differences in modality contribution.
Methods: To address these limitations, this study proposed a lightweight RGB–VNIR dual-modal fusion framework for fine-grained quality-category classification of Canadian wild rice kernels. A Coordinate Attention-enhanced MobileNetV3-Small was employed to extract spatial phenotypic features, while a 1D-GhostResNet-SE was used to model continuous VNIR spectral responses. A Cross-Modal Contribution-Aware Recalibration Fusion Head (CMCR-FH) was further introduced to adaptively regulate the contributions of the two modalities. The framework was evaluated on 2,048 paired RGB–VNIR samples from eight categories using stratified five-fold cross-validation.
Results: The proposed framework achieved a mean accuracy of 98.68% ± 0.22% and a Macro-F1 score of 98.69% ± 0.22%, representing numerical improvements of 4.93 and 4.97 percentage points, respectively, over the baseline model, while requiring only 1.236 M parameters and 63.537 M multiply–accumulate operations. Ablation experiments demonstrated complementary contributions from visual feature enhancement, lightweight spectral representation, and sample-adaptive multimodal fusion, with CMCR-FH producing the largest numerical performance gain among the evaluated components. Grad-CAM++ and SHAP analyses further indicated that the model jointly utilized visible phenotypic abnormalities and class-dependent spectral response patterns for discrimination.
Discussion: These results demonstrate that integrating complementary RGB and VNIR information with sample-adaptive fusion can improve fine-grained quality-category classification while maintaining low computational complexity. The proposed framework provides an effective balance among classification accuracy, computational efficiency, and interpretability, offering a promising approach for multimodal postharvest quality-category classification and grading of Canadian wild rice kernels.
Related
- An integrated machine learning framework for accurate, real-time and non-destructive vitamin C quantification from Vis/NIR spectral data
- Near-infrared spectroscopy for rapid and non-destructive assessment of PFAS effects in blue mussels (Mytilus spp.): a proof-of-concept study
- Multimodal Sensor Fusion for Non-Destructive Tea Quality Evaluation: Deep Learning-Enabled Methods, Applications, and Challenges
- CampChem: Rubric-Grounded Adaptive Campaigns for Multi-Round Organic Synthesis with Residual Spectral Observation
- A post-marketing assessment of critical quality and short-term stability attributes of heat-stable carbetocin injection products marketed in India
BibTeX
@article{qiao2026adaptive,
title = {{Adaptive RGB–VNIR spectral fusion for non-destructive quality assessment of Canadian wild rice kernels}},
author = {Zhenhua Qiao and Jinting Zou and Dongxu Wang and Chunyun Wang},
journal = {Frontiers in plant science},
year = {2026},
month = oct,
doi = {10.3389/fpls.2026.1973124},
url = {https://europepmc.org/article/PMC/PMC13669176},
note = {CC BY},
}
RIS
TY - JOUR
TI - Adaptive RGB–VNIR spectral fusion for non-destructive quality assessment of Canadian wild rice kernels
AU - Zhenhua Qiao
AU - Jinting Zou
AU - Dongxu Wang
AU - Chunyun Wang
PY - 2026
DA - 2026/10/01
JO - Frontiers in plant science
DO - 10.3389/fpls.2026.1973124
UR - https://europepmc.org/article/PMC/PMC13669176
AB - Introduction: Canadian wild rice kernels exhibit diverse postharvest variations, including breakage, discoloration, insect damage, and incomplete dehulling, making accurate and non-destructive classification important for screening and grading. However, RGB imaging may be insufficient for distinguishing kernels with subtle or overlapping visual characteristics, while visible–near-infrared (VNIR) spectra provide complementary information but contain substantial redundancies. Moreover, conventional multimodal fusion strategies based on direct concatenation or fixed weighting cannot readily adapt to sample-specific differences in modality contribution. Methods: To address these limitations, this study proposed a lightweight RGB–VNIR dual-modal fusion framework for fine-grained quality-category classification of Canadian wild rice kernels. A Coordinate Attention-enhanced MobileNetV3-Small was employed to extract spatial phenotypic features, while a 1D-GhostResNet-SE was used to model continuous VNIR spectral responses. A Cross-Modal Contribution-Aware Recalibration Fusion Head (CMCR-FH) was further introduced to adaptively regulate the contributions of the two modalities. The framework was evaluated on 2,048 paired RGB–VNIR samples from eight categories using stratified five-fold cross-validation. Results: The proposed framework achieved a mean accuracy of 98.68% ± 0.22% and a Macro-F1 score of 98.69% ± 0.22%, representing numerical improvements of 4.93 and 4.97 percentage points, respectively, over the baseline model, while requiring only 1.236 M parameters and 63.537 M multiply–accumulate operations. Ablation experiments demonstrated complementary contributions from visual feature enhancement, lightweight spectral representation, and sample-adaptive multimodal fusion, with CMCR-FH producing the largest numerical performance gain among the evaluated components. Grad-CAM++ and SHAP analyses further indicated that the model jointly utilized visible phenotypic abnormalities and class-dependent spectral response patterns for discrimination. Discussion: These results demonstrate that integrating complementary RGB and VNIR information with sample-adaptive fusion can improve fine-grained quality-category classification while maintaining low computational complexity. The proposed framework provides an effective balance among classification accuracy, computational efficiency, and interpretability, offering a promising approach for multimodal postharvest quality-category classification and grading of Canadian wild rice kernels.
SN - 1664-462X
ER -