{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T07:05:26Z","timestamp":1773731126158,"version":"3.50.1"},"reference-count":37,"publisher":"MDPI AG","issue":"18","license":[{"start":{"date-parts":[[2020,9,17]],"date-time":"2020-09-17T00:00:00Z","timestamp":1600300800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Hyperspectral imaging (HSI) emerges as a non-destructive and rapid analytical tool for assessing food quality, safety, and authenticity. This work aims to investigate the potential of combining the spectral and spatial features of HSI data with the aid of deep learning approach for the pixel-wise classification of food products. We applied two strategies for extracting spatial-spectral features: (1) directly applying three-dimensional convolution neural network (3-D CNN) model; (2) first performing principal component analysis (PCA) and then developing 2-D CNN model from the first few PCs. These two methods were compared in terms of efficiency and accuracy, exemplified through two case studies, i.e., classification of four sweet products and differentiation between white stripe (\u201cmyocommata\u201d) and red muscle (\u201cmyotome\u201d) pixels on salmon fillets. Results showed that combining spectral-spatial features significantly enhanced the overall accuracy for sweet dataset, compared to partial least square discriminant analysis (PLSDA) and support vector machine (SVM). Results also demonstrated that spectral pre-processing techniques prior to CNN model development can enhance the classification performance. This work will open the door for more research in the area of practical applications in food industry.<\/jats:p>","DOI":"10.3390\/s20185322","type":"journal-article","created":{"date-parts":[[2020,9,17]],"date-time":"2020-09-17T08:29:43Z","timestamp":1600331383000},"page":"5322","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":30,"title":["Deep Spectral-Spatial Features of Near Infrared Hyperspectral Images for Pixel-Wise Classification of Food Products"],"prefix":"10.3390","volume":"20","author":[{"given":"Hongyan","family":"Zhu","sequence":"first","affiliation":[{"name":"College of Electronic Engineering, Guangxi Normal University, Guilin 541004, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9494-2204","authenticated-orcid":false,"given":"Aoife","family":"Gowen","sequence":"additional","affiliation":[{"name":"UCD School of Biosystems and Food Engineering, University College of Dublin (UCD), Belfield, Dublin 4, Ireland"}]},{"given":"Hailin","family":"Feng","sequence":"additional","affiliation":[{"name":"School of Information Engineering, Zhejiang Agricultural and Forestry University, Hangzhou 310000, China"}]},{"given":"Keping","family":"Yu","sequence":"additional","affiliation":[{"name":"Global Information and Telecommunication Institute, Waseda University, Shinjuku, Tokyo 169-8050, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4442-7538","authenticated-orcid":false,"given":"Jun-Li","family":"Xu","sequence":"additional","affiliation":[{"name":"UCD School of Biosystems and Food Engineering, University College of Dublin (UCD), Belfield, Dublin 4, Ireland"}]}],"member":"1968","published-online":{"date-parts":[[2020,9,17]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1147","DOI":"10.1126\/science.228.4704.1147","article-title":"Imaging spectrometry for earth remote sensing","volume":"228","author":"Goetz","year":"1985","journal-title":"Science"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"71","DOI":"10.1016\/j.scijus.2013.09.005","article-title":"Hyperspectral imaging of gel pen inks: An emerging tool in document analysis","volume":"54","author":"Reed","year":"2014","journal-title":"Sci. Justice"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"136","DOI":"10.1016\/j.chemolab.2016.11.004","article-title":"Unveiling multiple solid-state transitions in pharmaceutical solid dosage forms using multi-series hyperspectral imaging and different curve resolution approaches","volume":"161","author":"Alexandrino","year":"2017","journal-title":"Chemom. Intell. Lab."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1016\/j.jspr.2015.01.006","article-title":"Hyperspectral imaging to classify and monitor quality of agricultural materials","volume":"61","author":"Mahesh","year":"2015","journal-title":"J. Stored Prod. Res."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"149","DOI":"10.1016\/j.ijrefrig.2016.10.014","article-title":"Identification of freezer burn on frozen salmon surface using hyperspectral imaging and computer vision combined with machine learning algorithm","volume":"74","author":"Xu","year":"2017","journal-title":"Int. J. Refrig."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1016\/j.talanta.2015.01.012","article-title":"Recent applications of hyperspectral imaging in microbiology","volume":"137","author":"Gowen","year":"2015","journal-title":"Talanta"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"166","DOI":"10.1002\/cem.785","article-title":"Partial least squares for discrimination","volume":"17","author":"Barker","year":"2003","journal-title":"J. Chemom."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"281","DOI":"10.1016\/j.jfoodeng.2012.05.038","article-title":"Grading and color evolution of apples using RGB and hyperspectral imaging vision cameras","volume":"113","author":"Amigo","year":"2012","journal-title":"J. Food Eng."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"342","DOI":"10.1016\/j.jfoodeng.2013.02.022","article-title":"Detection of expired vacuum-packed smoked salmon based on PLS-DA method using hyperspectral images","volume":"117","author":"Ivorra","year":"2013","journal-title":"J. Food Eng."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1016\/j.isprsjprs.2019.09.006","article-title":"Deep learning classifiers for hyperspectral imaging: A review","volume":"158","author":"Paoletti","year":"2019","journal-title":"ISPRS J. Photogramm."},{"key":"ref_11","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"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"159","DOI":"10.1109\/MGRS.2019.2912563","article-title":"Deep learning for classification of hyperspectral data: A comparative review","volume":"7","author":"Audebert","year":"2019","journal-title":"IEEE Geosci. Remote Sens. Mag."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1016\/j.neunet.2014.09.003","article-title":"Deep learning in neural networks: An overview","volume":"61","author":"Schmidhuber","year":"2015","journal-title":"Neural Networks"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"8","DOI":"10.1109\/MGRS.2017.2762307","article-title":"Deep learning in remote sensing: A comprehensive review and list of resources","volume":"5","author":"Zhu","year":"2017","journal-title":"IEEE Geosci. Remote Sens. Mag."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"7170","DOI":"10.1109\/TGRS.2019.2911993","article-title":"A CNN-based spatial feature fusion algorithm for hyperspectral imagery classification","volume":"57","author":"Guo","year":"2019","journal-title":"IEEE Trans. Geosci. Remote"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1155\/2015\/258619","article-title":"Deep convolutional neural networks for hyperspectral image classification","volume":"2015","author":"Hu","year":"2015","journal-title":"J. Sensors"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"6232","DOI":"10.1109\/TGRS.2016.2584107","article-title":"Deep feature extraction and classification of hyperspectral images based on convolutional neural networks","volume":"54","author":"Chen","year":"2016","journal-title":"IEEE Trans. Geosci. Remote"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"4420","DOI":"10.1109\/TGRS.2018.2818945","article-title":"3-D deep learning approach for remote sensing image classification","volume":"56","author":"Hamida","year":"2018","journal-title":"IEEE Trans. Geosci. Remote"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Li, Y., Zhang, H., and Shen, Q. (2017). Spectral\u2013spatial classification of hyperspectral imagery with 3D convolutional neural network. Remote Sens., 9.","DOI":"10.3390\/rs9010067"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Al-Sarayreh, M., Reis, M., Yan, W.Q., and Klette, R. (2020). Potential of deep learning and snapshot hyperspectral imaging for classification of species in meat. Food Control, 117.","DOI":"10.1016\/j.foodcont.2020.107332"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1007\/s12161-017-0957-4","article-title":"Computer vision detection of salmon muscle gaping using convolutional neural network features","volume":"11","author":"Xu","year":"2018","journal-title":"Food Anal. Methods"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"104","DOI":"10.1007\/s002170050466","article-title":"Use of image analysis to determine fat and connective tissue in salmon muscle","volume":"209","author":"Hurtado","year":"1999","journal-title":"Eur. Food Res. Technol."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"247","DOI":"10.1255\/jnirs.851","article-title":"Fat distribution analysis in salmon fillets using non-contact near infrared interactance imaging: A sampling and calibration strategy","volume":"17","author":"Segtnan","year":"2009","journal-title":"J. Near Infrared Spec."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1016\/j.jfoodeng.2015.08.015","article-title":"Efficient integration of particle analysis in hyperspectral imaging for rapid assessment of oxidative degradation in salmon fillet","volume":"169","author":"Xu","year":"2016","journal-title":"J. Food Eng."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"1201","DOI":"10.1016\/j.trac.2009.07.007","article-title":"Review of the most common pre-processing techniques for near-infrared spectra","volume":"28","author":"Rinnan","year":"2009","journal-title":"TrAC Trend Anal. Chem."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"1109","DOI":"10.1016\/j.addr.2005.01.020","article-title":"Near-infrared spectroscopy and imaging: Basic principles and pharmaceutical applications","volume":"57","author":"Reich","year":"2005","journal-title":"Adv. Drug Deliv. Rev."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"191","DOI":"10.1016\/S0169-7439(03)00051-0","article-title":"EPO\u2013PLS external parameter orthogonalisation of PLS application to temperature-independent measurement of sugar content of intact fruits","volume":"66","author":"Roger","year":"2003","journal-title":"Chemom. Intell. Lab."},{"key":"ref_28","unstructured":"Martens, H., and N\u00e6s, T. (2011). Pretreatment and linearization. Multivariate Calibration, John Wiley & Sons Ltd."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"92","DOI":"10.1016\/j.geoderma.2015.12.014","article-title":"Moisture insensitive prediction of soil properties from VNIR reflectance spectra based on external parameter orthogonalization","volume":"267","author":"Wijewardane","year":"2016","journal-title":"Geoderma"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Brereton, R.G., and Lloyd, G.R. (2018). Partial least squares discriminant analysis for chemometrics and metabolomics: How scores, loadings, and weights differ according to two common algorithms. J. Chemom., 32.","DOI":"10.1002\/cem.3028"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"375","DOI":"10.1002\/cem.1349","article-title":"Preventing over-fitting in PLS calibration models of near-infrared (NIR) spectroscopy data using regression coefficients","volume":"25","author":"Gowen","year":"2011","journal-title":"J. Chemom."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"675","DOI":"10.1016\/j.dsp.2006.11.009","article-title":"ECG beats classification using multiclass support vector machines with error correcting output codes","volume":"17","year":"2007","journal-title":"Digit. Signal Process."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"263","DOI":"10.1613\/jair.105","article-title":"Solving multiclass learning problems via error-correcting output codes","volume":"2","author":"Dietterich","year":"1994","journal-title":"J. Artif. Intell. Res."},{"key":"ref_34","unstructured":"Sokolova, M., and van Beek, P. (2014). Analysis of Feature Maps Selection in Supervised Learning Using Convolutional Neural Networks. Advances in Artificial Intelligence. Canadian AI 2014. Lecture Notes in Computer Science, Springer."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"458","DOI":"10.1007\/BF02977676","article-title":"Determination of water content in skin by using a FT near infrared spectrometer","volume":"28","author":"Suh","year":"2005","journal-title":"Arch. Pharm. Res."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"713","DOI":"10.1016\/S0309-1740(02)00273-5","article-title":"Determination of fatty acids in the subcutaneous fat of Iberian breed swine by near infrared spectroscopy (NIRS) with a fibre-optic probe","volume":"65","year":"2003","journal-title":"Meat Sci."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Xu, J.L., and Gowen, A.A. (2020). Spatial-spectral analysis method using texture features combined with PCA for information extraction in hyperspectral images. J. Chemom., 34.","DOI":"10.1002\/cem.3132"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/20\/18\/5322\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T10:11:00Z","timestamp":1760177460000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/20\/18\/5322"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,9,17]]},"references-count":37,"journal-issue":{"issue":"18","published-online":{"date-parts":[[2020,9]]}},"alternative-id":["s20185322"],"URL":"https:\/\/doi.org\/10.3390\/s20185322","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,9,17]]}}}