{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T20:01:20Z","timestamp":1791576080554,"version":"4.3.4"},"reference-count":53,"publisher":"MDPI AG","issue":"6","license":[{"start":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T00:00:00Z","timestamp":1781740800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000780","name":"European Union","doi-asserted-by":"crossref","award":["101138789"],"award-info":[{"award-number":["101138789"]}],"id":[{"id":"10.13039\/501100000780","id-type":"DOI","asserted-by":"crossref"}]},{"award":["101138789"],"award-info":[{"award-number":["101138789"]}],"id":[{"id":"https:\/\/ror.org\/019w4f821","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J. Imaging"],"abstract":"<jats:p>Recent advancements in computer vision, particularly in detection, segmentation, and classification, have significantly impacted various domains. However, these advancements are still strongly tied to RGB-based systems, which are insufficient for applications in industries such as waste sorting, pharmaceuticals, and defence, where material characterization beyond shape or visible colour is necessary. Hyperspectral (HS) imaging captures spatial and spectral information for each pixel and therefore offers a promising route for material-level classification. This study evaluates the potential of combining HS imaging with deep learning for plastic material classification. The work includes: (i) the design of an experimental setup with a HS line-scan camera, conveyor, and controlled illumination; (ii) the construction of an object-disjoint dataset of HDPE, PET, PP, and PS samples with semi-automated mask generation and Raman spectroscopy-based labelling; and (iii) the development of P1CH, a lightweight pixel-wise 1D convolutional hyperspectral classifier. On object-disjoint test images, P1CH achieved 97.44% all-pixel accuracy. A boundary sensitivity analysis, reported separately because semi-automated labels are uncertain at material\/background interfaces, yielded 99.94% accuracy after excluding a pre-defined two-pixel border band. Additional ablation, baseline, and robustness analyses show that the proposed pixel-wise spectral approach is effective for small fragments, visually similar plastics, and overlapping materials, while black or very dark plastics remain challenging under the present camera and illumination configuration.<\/jats:p>","DOI":"10.3390\/jimaging12060267","type":"journal-article","created":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T10:25:34Z","timestamp":1781778334000},"page":"267","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["A Deep Learning Approach for Pixel-Level Material Classification via Hyperspectral Imaging"],"prefix":"10.3390","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-5838-4317","authenticated-orcid":false,"given":"Savvas","family":"Sifnaios","sequence":"first","affiliation":[{"name":"Institute of Communication and Computer Systems, National Technical University of Athens, 9 Iroon Polytechniou Str., GR-157 73 Athens, Greece"},{"name":"School of Electrical and Computing Engineering, National Technical University of Athens, 9 Iroon Polytechniou Str., GR-157 73 Athens, Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"George","family":"Arvanitakis","sequence":"additional","affiliation":[{"name":"Technology Innovation Institute, Yas Island, Abu Dhabi P.O. Box 9639, United Arab Emirates"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1826-6582","authenticated-orcid":false,"given":"Fotios K.","family":"Konstantinidis","sequence":"additional","affiliation":[{"name":"Institute of Communication and Computer Systems, National Technical University of Athens, 9 Iroon Polytechniou Str., GR-157 73 Athens, Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Georgios","family":"Tsimiklis","sequence":"additional","affiliation":[{"name":"Institute of Communication and Computer Systems, National Technical University of Athens, 9 Iroon Polytechniou Str., GR-157 73 Athens, Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4089-1990","authenticated-orcid":false,"given":"Angelos","family":"Amditis","sequence":"additional","affiliation":[{"name":"Institute of Communication and Computer Systems, National Technical University of Athens, 9 Iroon Polytechniou Str., GR-157 73 Athens, Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8607-5737","authenticated-orcid":false,"given":"Panayiotis","family":"Frangos","sequence":"additional","affiliation":[{"name":"School of Electrical and Computing Engineering, National Technical University of Athens, 9 Iroon Polytechniou Str., GR-157 73 Athens, Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,6,18]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"14118","DOI":"10.1109\/ACCESS.2018.2812999","article-title":"Modern trends in hyperspectral image analysis: A review","volume":"6","author":"Khan","year":"2018","journal-title":"IEEE Access"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Lu, B., Dao, P.D., Liu, J., He, Y., and Shang, J. (2020). Recent advances of hyperspectral imaging technology and applications in agriculture. Remote Sens., 12.","DOI":"10.3390\/rs12162659"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"109955","DOI":"10.1016\/j.patcog.2023.109955","article-title":"Attack-invariant attention feature for adversarial defense in hyperspectral image classification","volume":"145","author":"Shi","year":"2024","journal-title":"Pattern Recognit."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Grahn, H., and Geladi, P. (2007). Techniques and Applications of Hyperspectral Image Analysis, John Wiley & Sons.","DOI":"10.1002\/9780470010884"},{"key":"ref_5","unstructured":"Przestrzelski, B., Reddy, E., and Lord, S. (2018, January 24\u201327). Integrating experiential with technical: How materials science modules can help redefine the traditional engineering canon. Proceedings of the ASEE Annual Conference, Salt Lake City, UT, USA."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"9045","DOI":"10.15376\/biores.15.4.9045-9058","article-title":"Classification option for Korean traditional paper based on type of raw materials, using near-infrared spectroscopy and multivariate statistical methods","volume":"15","author":"Jang","year":"2020","journal-title":"BioResources"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1229","DOI":"10.1007\/s10845-019-01508-6","article-title":"Identification and classification of materials using machine vision and machine learning in the context of industry 4.0","volume":"31","author":"Penumuru","year":"2020","journal-title":"J. Intell. Manuf."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"176","DOI":"10.1016\/j.commatsci.2016.05.034","article-title":"Image driven machine learning methods for microstructure recognition","volume":"123","author":"Chowdhury","year":"2016","journal-title":"Comput. Mater. Sci."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"012081","DOI":"10.1088\/1742-6596\/2369\/1\/012081","article-title":"Machine learning for materials classifications from images","volume":"2369","author":"Zhang","year":"2022","journal-title":"J. Phys. Conf. Ser."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"100701","DOI":"10.1063\/5.0087381","article-title":"Image-based machine learning for materials science","volume":"132","author":"Zhang","year":"2022","journal-title":"J. Appl. Phys."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"11879","DOI":"10.1039\/D4NR01413H","article-title":"Unveiling Brain Disorders Using Liquid Biopsy and Raman Spectroscopy","volume":"16","author":"Ranasinghe","year":"2024","journal-title":"Nanoscale"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"15457","DOI":"10.1021\/acsnano.4c16037","article-title":"Machine Learning Interpretation of Optical Spectroscopy Using Peak-Sensitive Logistic Regression","volume":"19","author":"Wang","year":"2025","journal-title":"ACS Nano"},{"key":"ref_13","first-page":"977","article-title":"Machine Learning-Enhanced Hyperspectral Raman Imaging for Label-Free Molecular Atlas of Alzheimer\u2019s Brain","volume":"18","author":"Wang","year":"2026","journal-title":"ACS Appl. Mater. Interfaces"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1920","DOI":"10.1021\/acssensors.5c03074","article-title":"Noise Management of Surface-Enhanced Raman Spectroscopy Using Two-Dimensional Materials","volume":"11","author":"Ranasinghe","year":"2026","journal-title":"ACS Sens."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"8492","DOI":"10.1021\/acs.analchem.4c00383","article-title":"RamanSPy: An Open-Source Python Package for Integrative Raman Spectroscopy Data Analysis","volume":"96","author":"Georgiev","year":"2024","journal-title":"Anal. Chem."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Wei\u00df, J., and Santra, A. (2019, January 23\u201327). Material classification using 60-GHz radar and deep convolutional neural network. Proceedings of the 2019 International Radar Conference (RADAR), Toulon, France.","DOI":"10.1109\/RADAR41533.2019.171265"},{"key":"ref_17","first-page":"2407","article-title":"Deep learning for surface material classification using haptic and visual information","volume":"18","author":"Zheng","year":"2016","journal-title":"IEEE Trans. Autom. Sci. Eng."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"105150","DOI":"10.1016\/j.cities.2024.105150","article-title":"Smart bins for enhanced resource recovery and sustainable urban waste practices in smart cities: A systematic literature review","volume":"152","author":"Zoumpoulis","year":"2024","journal-title":"Cities"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Zoumpoulis, P., Konstantinidis, F.K., Tsimiklis, G., and Amditis, A. (2024). Advancing Urban Waste Management Using Industry 5.0 Principles: A Novel Smart Bin. Proceedings of the 2024 IEEE International Workshop on Metrology for Industry 4.0 & IoT (MetroInd4. 0 & IoT), IEEE.","DOI":"10.1109\/MetroInd4.0IoT61288.2024.10584247"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"607","DOI":"10.1016\/j.promfg.2019.05.086","article-title":"Intelligent waste classification system using deep learning convolutional neural network","volume":"35","author":"Adedeji","year":"2019","journal-title":"Procedia Manuf."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"2128","DOI":"10.1038\/s41598-018-20037-5","article-title":"Advanced steel microstructural classification by deep learning methods","volume":"8","author":"Azimi","year":"2018","journal-title":"Sci. Rep."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"107244","DOI":"10.1016\/j.resconrec.2023.107244","article-title":"Multi-modal sorting in plastic and wood waste streams","volume":"199","author":"Konstantinidis","year":"2023","journal-title":"Resour. Conserv. Recycl."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Shaikh, M., and Th\u00f6rnberg, B. (2022). Impact of water vapour on polymer classification using in situ short-wave infrared hyperspectral imaging. J. Spectr. Imaging.","DOI":"10.1255\/jsi.2022.a5"},{"key":"ref_24","first-page":"1","article-title":"Determination of concrete properties using hyperspectral imaging technology: A review","volume":"2013","author":"Shaban","year":"2013","journal-title":"Sci. J. Phys."},{"key":"ref_25","unstructured":"Capobianco, G., Prestileo, F., and Serranti, S. (2015, January 10\u201313). Hyperspectral imaging-based approach for the in-situ characterization of ancient Roman wall paintings. Proceedings of the International Conference on Image Processing Theory, Tools and Applications, Orleans, France."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.culher.2017.01.013","article-title":"Hyperspectral imaging combined with data classification techniques as an aid for artwork authentication","volume":"26","author":"Polak","year":"2017","journal-title":"J. Cult. Herit."},{"key":"ref_27","first-page":"2393","article-title":"An Intelligent Deep Learning Based Xception Model for Hyperspectral Image Analysis and Classification","volume":"67","author":"Banumathi","year":"2021","journal-title":"Comput. Mater."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"6690","DOI":"10.1109\/TGRS.2019.2907932","article-title":"Deep learning for hyperspectral image classification: An overview","volume":"57","author":"Li","year":"2019","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"2798","DOI":"10.1109\/TGRS.2017.2783886","article-title":"Pretraining for hyperspectral convolutional neural network classification","volume":"56","author":"Windrim","year":"2018","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"7048","DOI":"10.1109\/TGRS.2019.2910603","article-title":"Automatic design of convolutional neural network for hyperspectral image classification","volume":"57","author":"Chen","year":"2019","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"1975","DOI":"10.1109\/JSTARS.2017.2655516","article-title":"R-VCANet: A new deep-learning-based hyperspectral image classification method","volume":"10","author":"Pan","year":"2017","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"216","DOI":"10.1007\/s10916-019-1347-9","article-title":"Hyperspectral image features classification using deep learning recurrent neural networks","volume":"43","author":"Venkatesan","year":"2019","journal-title":"J. Med. Syst."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"3719","DOI":"10.1109\/TIP.2020.2965302","article-title":"Material based object tracking in hyperspectral videos","volume":"29","author":"Xiong","year":"2020","journal-title":"IEEE Trans. Image Process."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"107962","DOI":"10.1016\/j.foodcont.2021.107962","article-title":"Hyperspectral image classification using CNN: Application to industrial food packaging","volume":"125","author":"Medus","year":"2021","journal-title":"Food Control"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Okada, N., Maekawa, Y., Owada, N., Haga, K., Shibayama, A., and Kawamura, Y. (2020). Automated Identification of Mineral Types and Grain Size Using Hyperspectral Imaging and Deep Learning for Mineral Processing. Minerals, 10.","DOI":"10.3390\/min10090809"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"93028","DOI":"10.1109\/ACCESS.2020.2994913","article-title":"Online Sorting of the Film on Cotton Based on Deep Learning and Hyperspectral Imaging","volume":"8","author":"Ni","year":"2020","journal-title":"IEEE Access"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Zhu, S., Zhou, L., Gao, P., Bao, Y., He, Y., and Feng, L. (2019). Near-Infrared Hyperspectral Imaging Combined with Deep Learning to Identify Cotton Seed Varieties. Molecules, 24.","DOI":"10.3390\/molecules24183268"},{"key":"ref_38","unstructured":"Picon, A., Galan, P., Bereciartua-Perez, A., and del Valle, L.B. (2024). Hyperspectral Dataset and Deep Learning methods for Waste from Electric and Electronic Equipment Identification (WEEE). arXiv."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"277","DOI":"10.1109\/LGRS.2019.2918719","article-title":"HybridSN: Exploring 3D-2D CNN Feature Hierarchy for Hyperspectral Image Classification","volume":"17","author":"Roy","year":"2020","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Brady, D.J. (2009). Optical Imaging and Spectroscopy, John Wiley & Sons.","DOI":"10.1002\/9780470443736"},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Sifnaios, S., Zorzos, I., Arvanitakis, G., Konstantinidis, F.K., Tsimiklis, G., and Amditis, A. (2023). Exploration and Mitigation of the Impact of Lighting Conditions on Multi-spectral Image Classification. Proceedings of the 2023 IEEE International Conference on Imaging Systems and Techniques (IST), IEEE.","DOI":"10.1109\/IST59124.2023.10355660"},{"key":"ref_42","first-page":"3407","article-title":"A review of hyperspectral imaging-based plastic waste detection state-of-the-arts","volume":"13","author":"Tamin","year":"2023","journal-title":"Int. J. Electr. Comput. Eng."},{"key":"ref_43","unstructured":"Lindell, M. (2018). Pixel Classification of Hyperspectral Images. [Ph.D. Thesis, Uppsala University]."},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Yu, X., Sun, Y., Fang, A., Qi, W., and Liu, C. (2014, January 15\u201317). Laboratory spectral calibration and radiometric calibration of hyper-spectral imaging spectrometer. Proceedings of the The 2014 2nd International Conference on Systems and Informatics (ICSAI 2014), Shanghai, China.","DOI":"10.1109\/ICSAI.2014.7009407"},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"355","DOI":"10.1016\/S0734-189X(87)80186-X","article-title":"Adaptive histogram equalization and its variations","volume":"39","author":"Pizer","year":"1987","journal-title":"Comput. Vis. Graph. Image Process."},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Mintun, E., Ravi, N., Mao, H., Rolland, C., Gustafson, L., Xiao, T., Whitehead, S., Berg, A.C., and Lo, W.Y. (2023). Segment Anything. arXiv.","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Smith, E., and Dent, G. (2019). Modern Raman Spectroscopy: A Practical Approach, John Wiley & Sons.","DOI":"10.1002\/9781119440598"},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Long, D.A. (2002). The Raman Effect: A Unified Treatment of the Theory of Raman Scattering by Molecules, John Wiley & Sons.","DOI":"10.1002\/0470845767"},{"key":"ref_49","unstructured":"Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep Learning, MIT Press."},{"key":"ref_50","unstructured":"Serra, J. (1982). Image Analysis and Mathematical Morphology, Academic Press, Inc."},{"key":"ref_51","unstructured":"De la Torre, F., and Serra, J. (1984, January 4). Morphological filtering. Proceedings of the SPIE Proceedings, Image Processing, San Diego, CA, USA."},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"7831","DOI":"10.1109\/TGRS.2020.3043267","article-title":"Attention-Based Adaptive Spectral\u2013Spatial Kernel ResNet for Hyperspectral Image Classification","volume":"59","author":"Roy","year":"2021","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_53","first-page":"3","article-title":"Spectral Imaging for Remote Sensing","volume":"14","author":"Shaw","year":"2003","journal-title":"Linc. Lab. J."}],"container-title":["Journal of Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2313-433X\/12\/6\/267\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,20]],"date-time":"2026-06-20T04:25:27Z","timestamp":1781929527000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2313-433X\/12\/6\/267"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,18]]},"references-count":53,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2026,6]]}},"alternative-id":["jimaging12060267"],"URL":"https:\/\/doi.org\/10.3390\/jimaging12060267","relation":{},"ISSN":["2313-433X"],"issn-type":[{"value":"2313-433X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,18]]}}}