Application of hyperspectral imaging techniques for sorting coffee beans

Abstract

Aim: Green coffee processing, before the roasting phase, requires effective removal of foreign materials and defective kernels to ensure product quality, process safety, and compliance with industrial requirements. The aim of this research is to use conventional RGB-based optical sorters for product sorting. These rely primarily on surface colour characteristics and can be limited when contaminants display visual similarities to healthy beans. Methods: Hyperspectral imaging (HSI) provides a non-destructive alternative by integrating spatial and spectral information in the visible and near-infrared (VIS/NIR) range. In this study, a VIS/NIR HSI system was integrated into a commercial industrial optical sorter and validated under real operating conditions. Contaminated green coffee batches (10 kg) containing known amounts of organic and inorganic contaminants were processed through multiple sorting passes using a statistical classification logic embedded into the sorter programmable logic controller (PLC) for real-time decision making. Results: The system achieved complete removal of stone contaminants after a single pass, while organic contaminants (peel and defective beans) were substantially reduced across successive cycles. After two sorting passes, the cumulative yield of compliant coffee beans was approximately 84%, representing an acceptable trade-off between contaminant removal efficiency and product loss in an industrial context. Conclusions: Overall, the results support the feasibility of deploying VIS/NIR hyperspectral sensing for high-throughput industrial coffee sorting, with potential advantages in discrimination capability compared with conventional colour-based systems.

Keywords

hyperspectral imaging / VIS/NIR / industrial optical sorter / coffee / real-time classification

References

[1] European Coffee Report 2023—2024[Internet]. ECF; c2026 [cited 2025 Sep 2]. Available from: https://www.ecf—coffee.org/european—coffee—report—2023—2024/

[2] Farah A. Coffee Constituents. In: Chu YF, editor. Coffee: Emerging Health Effects and Disease Prevention. Hoboken: Wiley—Blackwell; 2012.

[3] Cheremisinoff NP. Chapter 6 Mechanical Separation Equipment. In: Handbook of Chemical Processing Equipment. Amsterdam: Elsevier; 2000. pp. 334-434.

[4] Ariana DP, Lu R. Quality evaluation of pickling cucumbers using hyperspectral reflectance and transmittance imaging: Part I. Development of a prototype. Sens Instrumen Food Qual. 2008;2:144-51.

[5] Tadhg B, Da—Wen S. Improving quality inspection of food products by computer vision——a review. J Food Eng. 2004;61:3-16.

[6] Blasco J, Aleixos N, Moltó E. Machine Vision System for Automatic Quality Grading of Fruit. Biosyst Eng. 2003;85:415—23.

[7] Juliano P, Gaber MAFM, Romaniello R, Tamborrino A, Berardi A, Leone A. Advances in Physical Technologies to Improve Virgin Olive Oil Extraction Efficiency in High—Throughput Production Plants. Food Eng Rev. 2023;15:625-42.

[8] Perone C, Romaniello R, Leone A, Catalano P, Tamborrino A. CFD Analysis of a Tubular Heat Exchanger for the Conditioning of Olive Paste. Appl Sci. 2021;11:1858.

[9] Romaniello R, Perone C, Tamborrino A, Berardi A, Leone A, Di Taranto A, et al. Additives Individuation in Raw Ham Using Image Analysis. Chem Eng Trans. 2021;87:217—22.

[10] Tamborrino A, Catalano F, Berardi A, Bianchi B. New modelling approach for the energy and steam consumption evaluation in a fresh pasta industry. Chem Eng Trans. 2021;87:409—14.

[11] Huang H, Liu L, Ngadi MO. Recent developments in hyperspectral imaging for assessment of food quality and safety. Sens (Basel). 2014;14:7248-76.

[12] Qin J, Kim M, Chao K, Chan D, Delwiche S, Cho B. Line—Scan Hyperspectral Imaging Techniques for Food Safety and Quality Applications. Appl Sci. 2017;7:125.

[13] Wu D, Sun D. Advanced applications of hyperspectral imaging technology for food quality and safety analysis and assessment: A review—Part II: Applications. Innov Food Sci Emerg Technol. 2013;19:15-28.

[14] Santos JR, Sarraguça MC, Rangel AOSS, Lopes JA. Evaluation of green coffee beans quality using near infrared spectroscopy: a quantitative approach. Food Chem. 2012;135:1828—35.

[15] Dias RCE, Valderrama P, Março PH, Dos Santos Scholz MB, Edelmann M, Yeretzian C. Data on roasted coffee with specific defects analyzed by infrared—photoacoustic spectroscopy and chemometrics. Data Brief. 2018;20:242-9.

[16] Jiang Z, Lv A, Zhong L, Yang J, Xu X, Li Y, et al. Rapid Prediction of Adulteration Content inAtractylodis rhizoma Based on Data and Image Features Fusions from Near—Infrared Spectroscopy and Hyperspectral Imaging Techniques . Foods. 2023;12:2904.

[17] Amodio M, Berardi A, Ricci I, Babellahi F, Colelli G. Use of hyperspectral imaging for the discrimination of artichoke by cultivar and harvest time. Acta Hortic. 2020;1284:165-72.

[18] Leone A, Berardi A, Antonelli G, Dellisanti CD, Tamborrino A. NIR Spectroscopy for the Online Monitoring of Water and Olive Oil Content in Pomace during the Extraction Process. ASI. 2024;7:96.

[19] Romaniello R, Barrasso AE, Berardi A, Perone C, Tamborrino A, Catalano F, et al. Hyperspectral imaging system to on—line monitoring the soy flour content in a functional pasta. J Agric Eng. 2023;54:1535.

[20] Romaniello R, Barrasso AE, Perone C, Tamborrino A, Berardi A, Leone A. Optimisation of an Industrial Optical Sorter of Legumes for Gluten—Free Production Using Hyperspectral Imaging Techniques. Foods. 2024;13:404.

[21] Kılıç K, Boyacı İH, Köksel H, Küsmenoğlu İ. A classification system for beans using computer vision system and artificial neural networks. J Food Eng. 2007;78:897-904.

[22] Beghi R, Giovenzana V, Civelli R, Cini E, Guidetti R. Characterisation of olive fruit for the milling process by using visible/near infrared spectroscopy. J Agricult Engineer. 2013;44:8.

[23] Lee H, Cho B, Kim MS, Lee W, Tewari J, Bae H, et al. Prediction of crude protein and oil content of soybeans using Raman spectroscopy. Sens Actuators B: Chem. 2013;185:694-700.

[24] Mendoza FA, Cichy KA, Sprague C, Goffnett A, Lu R, Kelly JD. Prediction of canned black bean texture (Phaseolus vulgaris L.) from intact dry seeds using visible/near infrared spectroscopy and hyperspectral imaging data. J Sci Food Agric. 2018;98:283-90.

[25] Wei X, Zheng W, Zhu S, Zhou S, Wu W, Xie Z. Application of terahertz spectrum and interval partial least squares method in the identification of genetically modified soybeans. Spectrochim Acta A Mol Biomol Spectrosc. 2020;238:118453.

[26] Perone C, Romaniello R, Leone A, Berardi A, Catalano P, Tamborrino A. CFD Analysis of a Tube—in—tube Heat Exchanger to Pre—heat Olive Pastes. Chem Eng Trans. 2021;87:253—8.

[27] Das M, Wan SY, Agus S. A review of machine learning in hyperspectral imaging for food safety. Vib Spectrosc. 2025;139:103828.

[28] Yang C, Guo Z, Barbin DF, Dai Z, Watson N, Povey M, et al. Hyperspectral Imaging and Deep Learning for Quality and Safety Inspection of Fruits and Vegetables: A Review. J Agric Food Chem. 2025;73:10019—35.