Near-Infrared Hyperspectral Imaging Applications in Food Analysis -- Improving Algorithms and Methodologies

2025-10-15

AI Summary

This study addresses the limited accuracy of joint spatial-spectral modeling in near-infrared hyperspectral imaging (NIR-HSI) for food quality analysis. To this end, we propose an enhanced 2D convolutional neural network (CNN) architecture featuring a dedicated spectral convolution layer that automatically learns optimal spectral preprocessing features, enabling end-to-end joint spatial-spectral modeling. Additionally, we develop two open-source Python tools that significantly accelerate partial least squares (PLS) modeling and cross-validation. Experimental results demonstrate that the proposed CNN outperforms conventional PLS in generating smooth, physically interpretable chemical distribution maps, while PLS remains competitive for predicting bulk average concentrations. Notably, this work represents the first integration of spectral-aware convolution into a 2D CNN for NIR-HSI–based food analysis. By releasing both the novel architecture and efficient modeling tools as open-source resources, this study advances non-destructive hyperspectral food inspection with both methodological innovation and practical technical support.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Multimodal Learning
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data
• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding

Abstract

This thesis investigates the application of near-infrared hyperspectral imaging (NIR-HSI) for food quality analysis. The investigation is conducted through four studies operating with five research hypotheses. For several analyses, the studies compare models based on convolutional neural networks (CNNs) and partial least squares (PLS). Generally, joint spatio-spectral analysis with CNNs outperforms spatial analysis with CNNs and spectral analysis with PLS when modeling parameters where chemical and physical visual information are relevant. When modeling chemical parameters with a 2-dimensional (2D) CNN, augmenting the CNN with an initial layer dedicated to performing spectral convolution enhances its predictive performance by learning a spectral preprocessing similar to that applied by domain experts. Still, PLS-based spectral modeling performs equally well for analysis of the mean content of chemical parameters in samples and is the recommended approach. Modeling the spatial distribution of chemical parameters with NIR-HSI is limited by the ability to obtain spatially resolved reference values. Therefore, a study used bulk mean references for chemical map generation of fat content in pork bellies. A PLS-based approach gave non-smooth chemical maps and pixel-wise predictions outside the range of 0-100%. Conversely, a 2D CNN augmented with a spectral convolution layer mitigated all issues arising with PLS. The final study attempted to model barley's germinative capacity by analyzing NIR spectra, RGB images, and NIR-HSI images. However, the results were inconclusive due to the dataset's low degree of germination. Additionally, this thesis has led to the development of two open-sourced Python packages. The first facilitates fast PLS-based modeling, while the second facilitates very fast cross-validation of PLS and other classical machine learning models with a new algorithm.

Problem

• Improving food quality analysis using near-infrared hyperspectral imaging algorithms
• Comparing CNN and PLS models for chemical parameter prediction in food
• Developing enhanced spectral modeling approaches for spatial chemical distribution

Innovation

• CNN with spectral convolution enhances predictive performance
• PLS-based spectral modeling for mean chemical content analysis
• Open-source Python packages for fast PLS and cross-validation