MWIR-4-Plastic: The Identification of Complex End-of-Life Industrial Plastic using Mid-wave Infrared Hyperspectral Imaging and Machine Learning
Authors: Elias Arbash, Andréa de Lima Ribeiro, Filipa Simões, Ahmed Jamal Afifi, Aldino Rizaldy, Yuleika Madriz, Samuel Thiele, Sandra Lorenz, +4 more
Organizations: Helmholtz-Zentrum Dresden-Rossendorf (HZDR) - Helmholtz Institute Freiberg for Resource Technology (HIF), Freiberg, Germany · University of Antwerp, Antwerp, Belgium · Remote Sensing and Geoinformatics, Freie Universität Berlin, Berlin, Germany · Faculty of Electrical and Computer Engineering, University of Iceland, 101 Reykjavik, Iceland · TU Bergakademie Freiberg, Germany
The automated sorting of shredded black plastics from end-of-life (EOF) industrial waste presents a significant challenge in recycling facilities, primarily due to the limitations of current sensing and analytical approaches. Existing studies predominantly rely on single-point contact-based mid-infrared spectroscopy or laboratory hyperspectral imaging (HSI) setups, which fail to provide the spatially resolved analysis necessary for fast, bulk processing. Moreover, available datasets are laboratory-controlled and focus on intact rather than shredded plastics, hindering further recycling refinement. Black industrial plastics, in particular, are underrepresented, while most classification pipelines depend on manual region selection and rule-based spectral matching, neglecting spatial information and modern deep learning (DL) methods. To address these gaps, we introduce the first publicly available HSI dataset of shredded black plastics from EOF vehicle, comprising four industrial polymers across 13 co-registered RGB, VNIR, SWIR, and MWIR scenes and their segmentation pipeline. We developed a multi-modal spectral-spatial framework that integrates foreground isolation, pixel-wise classification, and object-level majority voting. By adapting advanced hyperspectral transformers from earth observation and incorporating chemometric band selection, we achieve accurate classification of complex black plastics. The study establishes the first comprehensive benchmark using nine processing methods, including chemometric, machine learning, and DL architectures. To ensure reproducibility, the complete dataset and methodologies are publicly released, establishing a benchmark for a hyperspectral object-analysis pipeline in industrial inspection.
Figures & tables
Parameter / Property
Specim AsiaFENIX (VNIR)
Specim AsiaFENIX (SWIR)
Specim FX50 (MWIR)
JAI LT-400 CL
Wavelength range (nm)
400–970
970–2500
2700–5300
RGB
Bands
175
275
308
3
Spectral resolution (nm)
3.5
12
35
–
Spatial sampling (mm)
1.6
1.1
0.16
Illumination source
Halogen light bulb
Shielded Ni/Cr resistance wire
–
Calibration panel
Zenith Polymer Diffuse >99%
Coarse Aluminium, ∼93%
–
Table 1: The parameters of the acquisition sensors and the selected processing bands along with their physical phenomena.
Figure 1: The average spectra of the studied polymers including the 25% and 75% percentiles before (A and B) and after (C and D) SNV normalization.
Figure 2: Train-test split class distribution.
Figure 3: Overview of the scene processing pipeline. The RGB image is segmented using GroundingDINO and SAM to generate semantic and instance masks. Classifiers are trained and validated using the pixel-wise ground truth across four classes: Styrene ( ), PA ( ), PC ( ), and PP ( ). The resulting pixel-wise predictions are then aggregated via majority voting within each mask to produce semantic- and instance-level classifications. Green boxes highlight cases where instance segmentation resolves overlapping or touching objects that semantic segmentation merges into a single prediction.
Figure 4: The F1-score and Cohen’s Kappa for each of the tested models across the four classes and scenes in the test set. The blue ( ), red ( ), and green ( ) bars correspond to pixel-wise classification, semantic object segmentation, and instance-level segmentation, respectively.
Reliable polymer identification is essential for ensuring the quality and safety of recycled plastics, yet conventional sorting and spectroscopic techniques often struggle to deliver robust discrimination. Terahertz (THz) spectroscopy offers a promising alternative, providing high-resolution and non-destructive measurements. In this work, we leverage THz signals to classify 12 types of polymers, including pure polymers, multilayer films, commercial blends, and biopolymers. To handle the complexity of these spectral signals, we propose the Multi-Scale Feature Attention Network (MSFAN), a novel deep learning architecture tailored for THz data. The framework integrates feature gating for signal recalibration and multi-scale parallel convolutions to capture diverse frequency patterns. These features are further refined through cross-feature attention and attention pooling, enabling the model to intrinsically highlight the most informative THz regions. MSFAN consistently outperforms state-of-the-art models, reaching a classification accuracy of 85.2%. This study demonstrates the potential of combining THz spectroscopy with deep learning techniques for effective, scalable, and interpretable polymer classification.
Roshni Mahtani, Ilán Carretero, Laura Monroy +3
Instituto Universitario de Investigaci´on e Innovaci´on en Tecnolog´ıa Centarada en el Ser Humano, HumanTech, Universitat Polit`ecnica de Val`encia, Valencia, Spain · Department of Electronic Technology, Universidad Carlos III de Madrid, Legan´es, Spain · Artikode Intelligence S.L., Valencia, Spain
Recently, Hyperspectral Image (HSI) classification has attracted increasing attention in remote sensing. However, HSI data are inherently high-dimensional but low-rank, with discriminative information concentrated on a low-dimensional latent manifold. In real-world remote sensing scenarios, the superposition of multiple degradation factors disrupts this intrinsic manifold structure, driving samples away from their original low-dimensional distribution and introducing substantial redundant and non-discriminative variations. To better handle this challenge, this paper proposes a manifold-space diffusion framework (MSDiff) for robust hyperspectral classification under complex degradation conditions. Specifically, the proposed method first maps high-dimensional, degradation-affected HSI data into a compact low-dimensional manifold through a discriminative spectral-spatial reconstruction task, preserving class semantics and reducing redundant variations. A diffusion-based generative model is then applied to regularize the spectral-spatial distribution within the manifold, enabling progressive refinement and stabilization of latent features against residual degradations. The key advantage of the proposed framework lies in performing diffusion-based distribution modeling directly on the low-dimensional manifold, effectively decoupling degradation-induced disturbances from intrinsic discriminative structures and enhancing representation stability under complex degradations. Experimental results on multiple hyperspectral benchmarks demonstrate consistent performance improvements over state-of-the-art methods under diverse composite degradation settings. The code will be available at https://github.com/yangboxiang1207/MSDiff
Boxiang Yang, Ning Chen, Xia Yue +6
Institute of Remote Sensing and Geographic Information System, Peking University, Beijing 100871, China · Beijing Key Laboratory of Spatio-temporal Perception and Urban Resilience, Peking University, Beijing 100871, China · School of Computer Science and Engineering, Central South University, Changsha 410083, China +4
Micro- and nano-plastic particles (MPs/NPs) are ubiquitous environmental contaminants whose increasing abundance and potential health impacts have created an urgent need for rapid, label-free detection methods. As particle size decreases to the low-micrometer range, conventional optical and spectroscopic techniques become increasingly challenging because of limited throughput and/or complex sample preparation. In this work, we present a machine learning (ML)-assisted radio-frequency (RF) dielectric spectroscopic cytometry (DiSC) platform for the label-free detection and classification of MPs. Eight types of 10 μm nominal-diameter MP particles suspended in deionized (DI) water were characterized at four frequencies spanning 0.2-9 GHz. The measured alterations in RF scattering parameters (S-parameters), referenced to the carrier medium, were used to train supervised ML models for material classification, including the identification of MPs in mixed samples and saline-water environments. For eight MP classes suspended in DI water, the proposed method achieved macro-average F1-score, precision, and recall values exceeding 0.71. Furthermore, PET classification performance was largely maintained in saline carrier media containing 3.3% and 6.6% sea salt. These results demonstrate the feasibility of ML-assisted RF DiSC for rapid, single-particle MP classification in aqueous environments. Future work will focus on improving classification performance through enhanced RF calibration, increased spectral coverage, larger training datasets, and validation using environmentally aged and biologically contaminated microplastics.