Plastic Packaging Classification Based on Near-infrared Spectroscopy and MS-Mamba Model

GUAN Yibo; DU Xinyun; ZHANG Zhixia

doi:10.19554/j.cnki.1001-3563.2026.03.021

PDF(4534 KB)

Packaging Engineering ›› 2026, Vol. 47 ›› Issue (3) : 198-209. DOI: 10.19554/j.cnki.1001-3563.2026.03.021

Automatic and Intelligent Technology

Plastic Packaging Classification Based on Near-infrared Spectroscopy and MS-Mamba Model

GUAN Yibo^1a,*, DU Xinyun^1b, ZHANG Zhixia²

Author information +

History +

Abstract

The work aims to explore the potential of combining near-infrared (NIR) spectroscopy with a deep learning model for rapid material identification, to address the limitations of traditional detection methods for plastic packaging materials, such as low efficiency, high human dependency, and difficulty in distinguishing visually similar materials with subtle compositional differences. NIR spectral data were collected from representative plastic packaging materials, including PET, PE, PP, PVC, PLA, and PBS. The raw spectra were preprocessed using a multi-step strategy involving Savitzky-Golay smoothing, Standard Normal Variate Transformation (SNV), and Multiplicative Scatter Correction (MSC) to eliminate noise and scattering interference. Based on this, a classification model based on Multi-Scale Mamba (MS-Mamba) was constructed. This model leveraged the linear complexity advantage of the State Space Model (SSM), employing multi-scale convolutional branches and a gated fusion mechanism to simultaneously capture local texture features and global long-range dependencies in spectral sequences. To assess performance, the proposed method was compared with traditional machine learning models (PCA-SVM and PLS-DA) and deep learning models (LSTM and Transformer), with accuracy, precision, recall, and F1-score as evaluation metrics. The experimental results demonstrated that the MS-Mamba model significantly outperformed traditional machine learning (PCA-SVM, PLS-DA) and mainstream deep learning models (ResNet, Transformer) in both classification accuracy and stability. The test set accuracy, precision, recall, and F1 score reached 99.91%, 99.89%, 99.88%, and 99.88%, respectively, while exhibiting exceptional robustness in distinguishing highly similar materials such as PE and PP. The proposed approach enables rapid, non-destructive, and highly accurate identification of plastic packaging materials, providing a feasible and effective solution for automated inspection and sustainable recycling applications.

Key words

near-infrared spectroscopy / plastic packaging classification / multi-scale Mamba / deep learning / non-destructive identification

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations

GUAN Yibo, DU Xinyun, ZHANG Zhixia. Plastic Packaging Classification Based on Near-infrared Spectroscopy and MS-Mamba Model[J]. Packaging Engineering. 2026, 47(3): 198-209 https://doi.org/10.19554/j.cnki.1001-3563.2026.03.021

References

[1] 孟凡悦, 文悦, 李琛, 等. 生物基塑料包装需氧生物降解研究进展[J]. 中国塑料, 2024, 38(4): 109-115.
MENG F Y, WEN Y, LI C, et al.Research Progress in Aerobic Biodegradation of Bio-Based Plastic Packaging Materials[J]. China Plastics, 2024, 38(4): 109-115.
[2] HENRIKSEN M L, KARLSEN C B, KLARSKOV P, et al.Plastic Classification via In-Line Hyperspectral Camera Analysis and Unsupervised Machine Learning[J]. Vibrational Spectroscopy, 2022, 118: 103329.
[3] PLETL A, KULKO R D, HANUS A, et al.A Plastic Classification Model Based on Simulated Data[J]. Recycling, 2025, 10(2): 65.
[4] RAMKUMAR M, BALASUBRAMANI K, SANTOSH M, et al.The Plastisphere: A Morphometric Genetic Classification of Plastic Pollutants in the Natural Environment[J]. Gondwana Research, 2022, 108: 4-12.
[5] CARRERA B, PIÑOL V L, MATA J B, et al. A Machine Learning Based Classification Models for Plastic Recycling Using Different Wavelength Range Spectrums[J]. Journal of Cleaner Production, 2022, 374: 133883.
[6] 张毅民, 刘红莎, 朱艳芳, 等. 废旧混合塑料识别分离与清洗技术研究进展[J]. 化工进展, 2013, 32(6): 1401-1406.
ZHANG Y M, LIU H S, ZHU Y F, et al.Development of Identification Separation and Cleaning Technologies for Mixed Waste Plastics[J]. Chemical Industry and Engineering Progress, 2013, 32(6): 1401-1406.
[7] PAN W, CHEN D Z, WANG G Y, et al.Impact of Classification and Resource Recovery on the Melting of Waste Pyrolysis Semi-Coke[J]. Environmental Sanitation Engineering, 2022, 30(2): 37-44.
[8] 熊越东, 黄华栋. 塑料瓶回收器的创新设计[J]. 机械工程师, 2012(11): 25-26.
XIONG Y D, HUANG H D.Innovative Design of Plastic Bottle Recycling Box[J]. Mechanical Engineer, 2012(11): 25-26.
[9] 李家帅, 薛莲莲, 王凯, 等. 基于近红外光谱的塑料分选技术预处理方法的优化[J]. 分析测试学报, 2023, 42(3): 351-356.
LI J S, XUE L L, WANG K, et al.Optimization of Pretreatment Methods for Plastic Sorting Technology Based on Near-Infrared Spectroscopy[J]. Journal of Instrumental Analysis, 2023, 42(3): 351-356.
[10] 胡锡敦, 尹禄, 杨钦晨, 等. 基于近红外高光谱成像技术的塑料分类[J]. 激光与光电子学进展, 2024, 61(2): 440-452.
HU X D, YIN L, YANG Q C, et al.Classification of Plastics Based on Near-Infrared Hyperspectral Imaging Technology(Invited)[J]. Laser & Optoelectronics Progress, 2024, 61(2): 440-452.
[11] 彭斌彬, 张潮, 郭亚坤, 等. 基于近红外光谱的废旧塑料材质识别研究[J]. 激光杂志, 2025, 46(2): 210-217.
PENG B B, ZHANG C, GUO Y K, et al.Study on the Identification of Waste Plastic Materials Based on near Infrared Spectroscopy[J]. Laser Journal, 2025, 46(2): 210-217.
[12] 房家萱, 董茜文, 徐梓睿, 等. 一种基于激光光谱融合检测技术的废旧塑料分类方法[J]. 光谱学与光谱分析, 2025, 45(9): 2484-2490.
FANG J X, DONG Q W, XU Z R, et al.A Waste Plastic Classification Method Based on Laser Spectral Fusion Detection Technology[J]. Spectroscopy and Spectral Analysis, 2025, 45(9): 2484-2490.
[13] 李冬怡, 李春宇, 姜红, 等. X射线荧光光谱结合BP神经网络对护手霜塑料包装瓶的分类研究[J]. 实验与分析, 2025, 3(1): 15-22.
LI D Y, LI C Y, JIANG H, et al.Classification of Plastic Packaging Bottles for Hand Cream Using X-ray Fluorescence Spectroscopy Combined with BP Neural Network[J]. Experiment and Analysis, 2025, 3(1): 15-22
[14] 苑宁之, 陈少华, 牟涛涛. 拉曼光谱结合深度学习算法的塑料分类的研究[J]. 光学仪器, 2023, 45(5): 35-43.
YUAN N Z, CHEN S H, MU T T.Research on Classification of Plastics by Raman Spectroscopy Combined with Deep Learning Algorithm[J]. Optical Instruments, 2023, 45(5): 35-43.
[15] 邵恒煊, 马鸿钰, 谢璟怡, 等. 红外光谱结合机器学习识别垃圾中塑料的应用进展[J]. 应用化工, 2025, 54(5): 1266-1271.
SHAO H X, MA H Y, XIE J Y, et al.Application Progress of Infrared Spectroscopy Combined with Machine Learning for Identifying Plastics in Garbage[J]. Applied Chemical Industry, 2025, 54(5): 1266-1271.
[16] 刘俊安, 李嘉铭, 赵楠, 等. 主成分分析结合支持向量机辅助激光诱导击穿光谱对塑料快速分类识别[J]. 光谱学与光谱分析, 2021, 41(6): 1955-1960.
LIU J A, LI J M, ZHAO N, et al.Rapid Classification and Identification of Plastic Using Laser-Induced Breakdown Spectroscopy with Principal Component Analysis and Support Vector Machine[J]. Spectroscopy and Spectral Analysis, 2021, 41(6): 1955-1960.
[17] 郑志杰, 林振衡, 谢海鹤, 等. 基于卷积神经网络的工程塑料太赫兹光谱分类识别方法[J]. 光谱学与光谱分析, 2023, 43(5): 1387-1393.
ZHENG Z J, LIN Z H, XIE H H, et al.The Method of Terahertz Spectral Classification and Identification for Engineering Plastics Based on Convolutional Neural Network[J]. Spectroscopy and Spectral Analysis, 2023, 43(5): 1387-1393.
[18] 周飞翔, 姜红, 钟方昊, 等. 基于高光谱结合机器学习对塑料瓶盖的快速分类研究[J]. 上海塑料, 2024, 52(2): 54-59.
ZHOU F X, JIANG H, ZHONG F H, et al.Fast Identification of Plastic Bottle Caps Based on Hyperspectral Combined with Machine Learning[J]. Shanghai Plastics, 2024, 52(2): 54-59.
[19] 李冬怡, 李春宇, 姜红, 等. 拉曼光谱结合1D-CNN的护手霜塑料包装分类研究[J]. 实验与分析, 2025, 3(2): 60-67.
LI D Y, LI C Y, JIANG H, et al.Research on the Classification of Hand Cream Plastic Packaging Using Raman Spectroscopy Combined with 1D-CNN[J]. Experiment and Analysis, 2025, 3(2): 60-67
[20] YANG J R, WANG J, LU G D, et al.TeaNet: Deep Learning on Near-Infrared Spectroscopy (NIR) Data for the Assurance of Tea Quality[J]. Computers and Electronics in Agriculture, 2021, 190: 106431.
[21] NUNEKPEKU X, ZHANG W, GAO J Y, et al.Gel Strength Prediction in Ultrasonicated Chicken Mince: Fusing Near-Infrared and Raman Spectroscopy Coupled with Deep Learning LSTM Algorithm[J]. Food Control, 2025, 168: 110916.
[22] 司坤宇, 牛春晖. 基于混合差分卷积和高效视觉Transformer网络的三重多模态图像融合算法[J]. 红外与激光工程, 2024, 53(11): 20240305.
SI K Y, NIU C H.Triple Multi-Modal Image Fusion Algorithm Based on Mixed Difference Convolution and Efficient Vision Transformer Network[J]. Infrared and Laser Engineering, 2024, 53(11): 20240305.
[23] YAO J, HONG D, LI C, et al.SpectralMamba: Efficient Mamba for Hyperspectral Image Classification[J]. arXiv preprint, 2024.
[24] ALKILANE K, HE Y H, LEE D H.MixMamba: Time Series Modeling with Adaptive Expertise[J]. Information Fusion, 2024, 112: 102589.
[25] GU A, DAO T. Mamba: Linear-Time Sequence Modeling with Selective State Spaces[J]. arXiv preprint, arXiv:2312.00752, 2023.
[26] 宁鸿章, 谭鑫, 李宇航, 等. 空-谱维联合Savitzky-Golay高光谱滤波算法及其应用[J]. 光谱学与光谱分析, 2020, 40(12): 3699-3704.
NING H Z, TAN X, LI Y H, et al.Joint Space-Spectrum SG Filtering Algorithms for Hyperspectral Images and Its Application[J]. Spectroscopy and Spectral Analysis, 2020, 40(12): 3699-3704.
[27] CHI K P, LIN J R, CHEN M, et al.Changeable Moving Window-Standard Normal Variable Transformation for Visible-NIR Spectroscopic Analyses[J]. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2024, 308: 123726.
[28] LI L, PENG Y K, LI Y Y, et al.A New Scattering Correction Method of Different Spectroscopic Analysis for Assessing Complex Mixtures[J]. Analytica Chimica Acta, 2019, 1087: 20-28.
[29] 李春艳, 王泞淋, 刘继红, 等. 基于多元散射校正的光谱共焦位移测量方法分析与研究[J]. 红外与激光工程, 2025, 54(1): 20240407.
LI C Y, WANG N L, LIU J H, et al.Analysis and Research of Spectral Confocal Displacement Measurement Method Based on Multiple Scattering Correction[J]. Infrared and Laser Engineering, 2025, 54(1): 20240407.
[30] 彭圆圆, 黎浩洋, 李文, 等. LTDA-Mamba: 基于CNN-Mamba混合网络的视网膜血管分割算法[J]. 光学学报, 2025, 45(7): 155-166.
PENG Y Y, LI H Y, LI W, et al.LTDA-Mamba: Retinal Vessel Segmentation Based on a Hybrid CNN-Mamba Network[J]. Acta Optica Sinica, 2025, 45(7): 155-166.
[31] ZHENG T T, YAO H X, ZHAO S C, et al.GraphMamba: Whole Slide Image Classification Meets Graph-Driven Selective State Space Model[J]. Pattern Recognition, 2025, 167: 111768.
[32] ZHANG H Y, LIU H, SHI Z X, et al.ConvMamba: Combining Mamba with CNN for Hyperspectral Image Classification[J]. Neurocomputing, 2025, 652: 131016.
[33] 田晨, 张金龙, 金义蓉, 等. 一种利用贝叶斯优化的蓝藻遥感分类方法[J]. 自然资源遥感, 2023, 35(1): 49-56.
TIAN C, ZHANG J L, JIN Y R, et al.A Remote Sensing Classification Method for Cyanobacteria Using Bayesian Optimization Algorithm[J]. Remote Sensing for Natural Resources, 2023, 35(1): 49-56.
[34] HUANG Q, YU H Y, JIANG Z H, et al.Multi-Component Quantitative Analysis of LIBS Using Adaptively Optimized Multi-Branch CNN[J]. Optics & Laser Technology, 2024, 179: 111282.