{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T17:30:09Z","timestamp":1783963809833,"version":"3.55.0"},"reference-count":57,"publisher":"MDPI AG","issue":"19","license":[{"start":{"date-parts":[[2020,10,7]],"date-time":"2020-10-07T00:00:00Z","timestamp":1602028800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>Hyperspectral imaging has many applications. However, the high device costs and low hyperspectral image resolution are major obstacles limiting its wider application in agriculture and other fields. Hyperspectral image reconstruction from a single RGB image fully addresses these two problems. The robust HSCNN-R model with mean relative absolute error loss function and evaluated by the Mean Relative Absolute Error metric was selected through permutation tests from models with combinations of loss functions and evaluation metrics, using tomato as a case study. Hyperspectral images were subsequently reconstructed from single tomato RGB images taken by a smartphone camera. The reconstructed images were used to predict tomato quality properties such as the ratio of soluble solid content to total titratable acidity and normalized anthocyanin index. Both predicted parameters showed very good agreement with corresponding \u201cground truth\u201d values and high significance in an F test. This study showed the suitability of hyperspectral image reconstruction from single RGB images for fruit quality control purposes, underpinning the potential of the technology\u2014recovering hyperspectral properties in high resolution\u2014for real-world, real time monitoring applications in agriculture any beyond.<\/jats:p>","DOI":"10.3390\/rs12193258","type":"journal-article","created":{"date-parts":[[2020,10,7]],"date-time":"2020-10-07T10:28:02Z","timestamp":1602066482000},"page":"3258","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":57,"title":["Deep Learning in Hyperspectral Image Reconstruction from Single RGB images\u2014A Case Study on Tomato Quality Parameters"],"prefix":"10.3390","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3916-7388","authenticated-orcid":false,"given":"Jiangsan","family":"Zhao","sequence":"first","affiliation":[{"name":"NIBIO\u2014Norwegian Institute of Bioeconomy Research, P.O. Box 115, N-1431 \u00c5s, Norway"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dmitry","family":"Kechasov","sequence":"additional","affiliation":[{"name":"Norwegian Institute of Bioeconomy Research, Postvegen 213, S\u00e6rheim, N-4353 Klepp Station, Norway"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8098-0616","authenticated-orcid":false,"given":"Boris","family":"Rewald","sequence":"additional","affiliation":[{"name":"Department of Forest and Soil Sciences, University of Natural Resources and Life Sciences, 1190 Vienna, Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9813-1364","authenticated-orcid":false,"given":"Gernot","family":"Bodner","sequence":"additional","affiliation":[{"name":"Division of Agronomy, Department of Crop Sciences, University of Natural Resources and Life Sciences, Konrad Lorenz-Stra\u00dfe 24, 3430 Tulln an der Donau, Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michel","family":"Verheul","sequence":"additional","affiliation":[{"name":"Norwegian Institute of Bioeconomy Research, Postvegen 213, S\u00e6rheim, N-4353 Klepp Station, Norway"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1588-9661","authenticated-orcid":false,"given":"Nicholas","family":"Clarke","sequence":"additional","affiliation":[{"name":"NIBIO\u2014Norwegian Institute of Bioeconomy Research, P.O. Box 115, N-1431 \u00c5s, Norway"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4924-0406","authenticated-orcid":false,"given":"Jihong Liu","family":"Clarke","sequence":"additional","affiliation":[{"name":"NIBIO\u2014Norwegian Institute of Bioeconomy Research, P.O. Box 115, N-1431 \u00c5s, Norway"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2020,10,7]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"285","DOI":"10.1080\/05704928.2018.1463235","article-title":"A review of hyperspectral imaging for nanoscale materials research","volume":"54","author":"Dong","year":"2019","journal-title":"Appl. Spectrosc. Rev."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"447","DOI":"10.1016\/j.lwt.2003.10.013","article-title":"Identification of animal meat muscles by visible and near infrared reflectance spectroscopy","volume":"37","author":"Cozzolino","year":"2004","journal-title":"LWT Food Sci. Technol."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"238","DOI":"10.1017\/S2040470017001248","article-title":"Plant disease detection by hyperspectral imaging: From the lab to the field","volume":"8","author":"Mahlein","year":"2017","journal-title":"Adv. Anim. Biosci."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1016\/j.still.2017.09.006","article-title":"Evaluating calibration methods for predicting soil available nutrients using hyperspectral VNIR data","volume":"175","author":"Qi","year":"2018","journal-title":"Soil Tillage Res."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1255\/jnirs.1199","article-title":"Near infrared spectroscopy in wildlife and biodiversity","volume":"24","author":"Vance","year":"2016","journal-title":"J. Near Infrared Spectrosc."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"11463","DOI":"10.1038\/s41598-017-11844-3","article-title":"Monitoring osteoarthritis progression using near infrared (NIR) spectroscopy","volume":"7","author":"Afara","year":"2017","journal-title":"Sci. Rep."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"213","DOI":"10.1007\/s10086-015-1467-x","article-title":"A review of recent application of near infrared spectroscopy to wood science and technology","volume":"61","author":"Tsuchikawa","year":"2015","journal-title":"J. Wood Sci."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"180","DOI":"10.1016\/j.ifset.2012.11.001","article-title":"Non-destructive assessment of microbial contamination in porcine meat using NIR hyperspectral imaging","volume":"17","author":"Barbin","year":"2013","journal-title":"Innov. Food Sci. Emerg. Technol."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"289","DOI":"10.1016\/j.biosystemseng.2013.01.004","article-title":"Laboratory vs. in-field spectral proximal sensing for early detection of Fusarium head blight infection in durum wheat","volume":"114","author":"Menesatti","year":"2013","journal-title":"Biosyst. Eng."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Signoroni, A., Savardi, M., Baronio, A., and Benini, S. (2019). Deep learning meets hyperspectral image analysis: A multidisciplinary review. J. Imaging, 5.","DOI":"10.3390\/jimaging5050052"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"2423","DOI":"10.1109\/TPAMI.2011.80","article-title":"A prism-mask system for multispectral video acquisition","volume":"33","author":"Cao","year":"2011","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1007\/s41348-017-0124-6","article-title":"Benefits of hyperspectral imaging for plant disease detection and plant protection: A technical perspective","volume":"125","author":"Thomas","year":"2018","journal-title":"J. Plant Dis. Prot."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"254","DOI":"10.1097\/ICU.0000000000000470","article-title":"Deep learning applications in ophthalmology","volume":"29","author":"Rahimy","year":"2018","journal-title":"Curr. Opin. Ophthalmol."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Rao, Q., and Frtunikj, J. (2018, January 28). Deep learning for self-driving cars: Chances and challenges. Proceedings of the 1st International Workshop on Software Engineering for AI in Autonomous Systems, Gothenburg, Sweden.","DOI":"10.1145\/3194085.3194087"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1525874","DOI":"10.34133\/2019\/1525874","article-title":"A weakly supervised deep learning framework for sorghum head detection and counting","volume":"2019","author":"Ghosal","year":"2019","journal-title":"Plant Phenomics"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Xiong, Z., Shi, Z., Li, H., Wang, L., Liu, D., and Wu, F. (2017, January 22\u201329). HSCNN: CNN-based hyperspectral image recovery from spectrally undersampled projections. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.","DOI":"10.1109\/ICCVW.2017.68"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Shi, Z., Chen, C., Xiong, Z., Liu, D., and Wu, F. (2018, January 18\u201322). HSCNN+: Advanced CNN-based hyperspectral recovery from rgb images. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPRW.2018.00139"},{"key":"ref_18","unstructured":"Arad, B., and Ben-Shahar, O. Sparse recovery of hyperspectral signal from natural RGB images. Proceedings of the European Conference on Computer Vision."},{"key":"ref_19","unstructured":"Galliani, S., Lanaras, C., Marmanis, D., Baltsavias, E., and Schindler, K. (2017). Learned spectral super-resolution. arXiv."},{"key":"ref_20","first-page":"s 206","article-title":"Low cost hyperspectral imaging using deep learning based spectral reconstruction","volume":"11257 LNCS","author":"Tschannerl","year":"2018","journal-title":"Lect. Notes Comput. Sci. (Including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics)"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Stiebel, T., Koppers, S., Seltsam, P., and Merhof, D. (2018, January 18\u201322). Reconstructing spectral images from rgb-images using a convolutional neural network. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Salt Lake City, UT, USA.","DOI":"10.1109\/CVPRW.2018.00140"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Nie, S., Gu, L., Zheng, Y., Lam, A., Ono, N., and Sato, I. (2018, January 18\u201322). Deeply learned filter response functions for hyperspectral reconstruction. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00501"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"98","DOI":"10.1186\/s13007-019-0479-8","article-title":"Plant disease identification using explainable 3D deep learning on hyperspectral images","volume":"15","author":"Nagasubramanian","year":"2019","journal-title":"Plant Methods"},{"key":"ref_24","unstructured":"Can, Y.B., and Timofte, R. (2018). An efficient CNN for spectral reconstruction from RGB images. arXiv."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Lai, J.H., Liu, C.L., Chen, X., Zhou, J., Tan, T., Zheng, N., and Zha, H. (2018). Accurate Spectral Super-Resolution from Single RGB Image Using Multi-scale CNN. Pattern Recognition and Computer Vision, Springer International Publishing.","DOI":"10.1007\/978-3-030-03398-9"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"197","DOI":"10.1146\/annurev-food-032818-121155","article-title":"Advanced techniques for hyperspectral imaging in the food industry: Principles and recent applications","volume":"10","author":"Ma","year":"2019","journal-title":"Annu. Rev. Food Sci. Technol."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1038\/s41438-018-0105-3","article-title":"Disassembly of the fruit cell wall by the ripening-associated polygalacturonase and expansin influences tomato cracking","volume":"6","author":"Jiang","year":"2019","journal-title":"Hortic. Res."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"117","DOI":"10.1016\/j.postharvbio.2004.05.002","article-title":"Measuring surface distribution of carotenes and chlorophyll in ripening tomatoes using imaging spectrometry","volume":"34","author":"Polder","year":"2004","journal-title":"Postharvest Biol. Technol."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"927","DOI":"10.1080\/15226510701375465","article-title":"Effects of nitrogen rates on chemical composition of yellow grape tomato grown in a subtropical climate","volume":"30","author":"Simonne","year":"2007","journal-title":"J. Plant Nutr."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"277","DOI":"10.1016\/j.jfoodeng.2011.07.021","article-title":"Investigation of Raman chemical imaging for detection of lycopene changes in tomatoes during postharvest ripening","volume":"107","author":"Qin","year":"2011","journal-title":"J. Food Eng."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"9813","DOI":"10.1021\/jf801299r","article-title":"Nondestructive measurement of fresh tomato lycopene content and other physicochemical characteristics using visible\u2014NIR spectroscopy","volume":"56","author":"Dorais","year":"2008","journal-title":"J. Agric. Food Chem."},{"key":"ref_32","first-page":"327","article-title":"On-tree and after-harvesting evaluation of firmness, color and lycopene content of tomato fruit using portable NIR spectroscopy","volume":"6","author":"Akinaga","year":"2008","journal-title":"J. Food Agric. Environ."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1016\/j.jfoodeng.2018.05.008","article-title":"Assessment of tomato soluble solids content and pH by spatially-resolved and conventional Vis\/NIR spectroscopy","volume":"236","author":"Huang","year":"2018","journal-title":"J. Food Eng."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Ntagkas, N., Min, Q., Woltering, E.J., Labrie, C., Nicole, C.C.S., and Marcelis, L.F.M. (2016, January 22\u201326). Illuminating tomato fruit enhances fruit vitamin C content. Proceedings of the VIII International Symposium on Light in Horticulture 1134, East Lansing, MI, USA.","DOI":"10.17660\/ActaHortic.2016.1134.46"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1016\/j.postharvbio.2012.05.008","article-title":"Low temperature-induced lycopene degradation in red ripe tomato evaluated by remittance spectroscopy","volume":"73","author":"Farneti","year":"2012","journal-title":"Postharvest Biol. Technol."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1016\/j.nut.2017.06.008","article-title":"Mediterranean diet and colorectal cancer: A systematic review","volume":"43","author":"Farinetti","year":"2017","journal-title":"Nutrition"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"2438","DOI":"10.1007\/s12161-019-01609-1","article-title":"Potential of Near-Infrared (NIR) spectroscopy and hyperspectral imaging for quality and safety assessment of fruits: An overview","volume":"12","author":"Chandrasekaran","year":"2019","journal-title":"Food Anal. Methods"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"1656","DOI":"10.3389\/fpls.2019.01656","article-title":"Supplemental LED inter-lighting increases tomato fruit growth through enhanced photosynthetic light use efficiency and modulated root activity","volume":"10","author":"Paponov","year":"2020","journal-title":"Front. Plant Sci."},{"key":"ref_39","first-page":"80","article-title":"Optimum procedures for ripening tomatoes","volume":"9","author":"Cantwell","year":"2000","journal-title":"Manag. Fruit Ripening Postharvest Hortic. Ser."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Behmann, J., Acebron, K., Emin, D., Bennertz, S., Matsubara, S., Thomas, S., Bohnenkamp, D., Kuska, M., Jussila, J., and Salo, H. (2018). Specim IQ: Evaluation of a new, miniaturized handheld hyperspectral camera and its application for plant phenotyping and disease detection. Sensors, 18.","DOI":"10.3390\/s18020441"},{"key":"ref_41","first-page":"1","article-title":"Methods for determining quality of fresh commodities","volume":"85","author":"Mitcham","year":"1996","journal-title":"Perishables Handl. Newsl."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"5026","DOI":"10.1021\/jf505450j","article-title":"From producer to consumer: Greenhouse tomato quality as affected by variety, maturity stage at harvest, transport conditions, and supermarket storage","volume":"63","author":"Verheul","year":"2015","journal-title":"J. Agric. Food Chem."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"12191","DOI":"10.3390\/s140712191","article-title":"On plant detection of intact tomato fruits using image analysis and machine learning methods","volume":"14","author":"Yamamoto","year":"2014","journal-title":"Sensors"},{"key":"ref_44","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (July, January 26). Deep residual learning for image recognition. Proceedings of the IEEE conference on computer vision and pattern recognition, Las Vegas, NV, USA."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"2019","DOI":"10.1016\/j.asr.2017.01.027","article-title":"Unsupervised change detection in a particular vegetation land cover type using spectral angle mapper","volume":"59","author":"Renza","year":"2017","journal-title":"Adv. Sp. Res."},{"key":"ref_46","unstructured":"Kingma, D.P., and Ba, J. (2014). Adam: A method for stochastic optimization. arXiv."},{"key":"ref_47","first-page":"31","article-title":"Package \u2018EnvStats\u2019","volume":"2","author":"Millard","year":"2018","journal-title":"Packag. Environ. Stat. Version"},{"key":"ref_48","unstructured":"R Core Team (2013). R: A Language and Environment for Statistical Computing, R Foundation for Statistical Computing."},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1007\/s11263-007-0090-8","article-title":"LabelMe: A database and web-based tool for image annotation","volume":"77","author":"Russell","year":"2008","journal-title":"Int. J. Comput. Vis."},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Goyal, P., Girshick, R., He, K., and Doll\u00e1r, P. (2017, January 22\u201329). Focal loss for dense object detection. Proceedings of the IEEE International Conference on Computer Vision (ICCV), Venice, Italy.","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1016\/j.chemolab.2012.02.006","article-title":"Suppressing sample morphology effects in near infrared spectral imaging using chemometric data pre-treatments","volume":"117","author":"Esquerre","year":"2012","journal-title":"Chemom. Intell. Lab. Syst."},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"1240","DOI":"10.1109\/JSTARS.2019.2901752","article-title":"An Efficient Residual Learning Neural Network for Hyperspectral Image Superresolution","volume":"12","author":"Liu","year":"2019","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_53","first-page":"3066","article-title":"Early fault detection in induction motors using AdaBoost with imbalanced small data and optimized sampling","volume":"53","year":"2016","journal-title":"IEEE Trans. Ind. Appl."},{"key":"ref_54","doi-asserted-by":"crossref","first-page":"195","DOI":"10.1002\/jsfa.1292","article-title":"Tomatine, chlorophyll, \u03b2-carotene and lycopene content in tomatoes during growth and maturation","volume":"83","author":"Kozukue","year":"2003","journal-title":"J. Sci. Food Agric."},{"key":"ref_55","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1016\/j.postharvbio.2014.05.007","article-title":"Quantifying lycopene synthesis and chlorophyll breakdown in tomato fruit using remittance VIS spectroscopy","volume":"96","author":"Schouten","year":"2014","journal-title":"Postharvest Biol. Technol."},{"key":"ref_56","doi-asserted-by":"crossref","first-page":"36005","DOI":"10.1117\/1.JRS.11.036005","article-title":"Remote sensing of key grassland nutrients using hyperspectral techniques in KwaZulu-Natal, South Africa","volume":"11","author":"Singh","year":"2017","journal-title":"J. Appl. Remote Sens."},{"key":"ref_57","doi-asserted-by":"crossref","unstructured":"Kawamura, K., Tsujimoto, Y., Rabenarivo, M., Asai, H., Andriamananjara, A., and Rakotoson, T. (2017). Vis-NIR spectroscopy and PLS regression with waveband selection for estimating the total C and N of paddy soils in Madagascar. Remote Sens., 9.","DOI":"10.3390\/rs9101081"}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/12\/19\/3258\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T10:17:12Z","timestamp":1760177832000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/12\/19\/3258"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10,7]]},"references-count":57,"journal-issue":{"issue":"19","published-online":{"date-parts":[[2020,10]]}},"alternative-id":["rs12193258"],"URL":"https:\/\/doi.org\/10.3390\/rs12193258","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,10,7]]}}}