Pine nut species recognition using NIR spectroscopy and image analysis

Abstract NIR spectroscopy and physical properties derived from image analysis were evaluated as potential features for the classification of seed kernels from two pine nut species (P. pinea L. and P. sibirica Du Tour) using Partial Least Squares Discriminant Analysis (PLS-DA). Model performances were evaluated in terms of specificity, sensitivity and accuracy. Data pre-treatments were essential for achieving excellent performances (accuracy rate > 95%) in all tests. The interval PLS-DA highlighted that the most important features for (1) the NIR method were the absorption bands at 1640–1658, 1720–1738 and 1880–1998 nm, while for (2) the image analysis were kernel eccentricity, kernel major axis length, kernel lightness (L*) and kernel perimeter. The results demonstrate potential of both techniques for discriminating the two pine nut species.

[1]  Paul Warren,et al.  Guidelines for the Development and Validation of Near‐Infrared Spectroscopic Methods in the Pharmaceutical Industry , 2006 .

[2]  Reema Valand,et al.  A review of Fourier Transform Infrared (FTIR) spectroscopy used in food adulteration and authenticity investigations , 2020, Food additives & contaminants. Part A, Chemistry, analysis, control, exposure & risk assessment.

[3]  G. Savage,et al.  Mineral Analysis of Pine Nuts (Pinus spp.) Grown in New Zealand , 2013, Foods.

[4]  Danilo Monarca,et al.  Effects of controlled atmospheres and low temperature on storability of chestnuts manually and mechanically harvested , 2011 .

[5]  Min Huang,et al.  Classification of maize seeds of different years based on hyperspectral imaging and model updating , 2016, Comput. Electron. Agric..

[6]  M. Pardos,et al.  Modelling spatiotemporal dynamics of Pinus pinea cone infestation by Dioryctria mendacella , 2017 .

[7]  Kurt Hornik,et al.  The Comprehensive R Archive Network , 2012 .

[8]  Massimo Cecchini,et al.  Hazelnut Quality Sorting Using High Dynamic Range Short-Wave Infrared Hyperspectral Imaging , 2015, Food and Bioprocess Technology.

[9]  Daniel E. Guyer,et al.  Comparison of transmittance and reflectance to detect insect infestation in Montmorency tart cherry , 2008 .

[10]  S. D. Jong.  SIMPLS: an alternative approach to partial least squares regression , 1993 .

[11]  Chu Zhang,et al.  Hyperspectral imaging analysis for ripeness evaluation of strawberry with support vector machine , 2016 .

[12]  W. Horwitz,et al.  Official methods of analysis of AOAC International , 2010 .

[13]  Lijuan Xie,et al.  Determination of toxigenic fungi and aflatoxins in nuts and dried fruits using imaging and spectroscopic techniques. , 2018, Food chemistry.

[14]  Zou Xiaobo,et al.  Variables selection methods in near-infrared spectroscopy. , 2010, Analytica chimica acta.

[15]  Federico Pallottino,et al.  Shape-based methodology for multivariate discrimination among Italian hazelnut cultivars , 2008 .

[16]  Federico Pallottino,et al.  Image Analysis Techniques for Automated Hazelnut Peeling Determination , 2010 .

[17]  Jerry Workman,et al.  Practical guide to interpretive near-infrared spectroscopy , 2007 .

[18]  O. Kvalheim,et al.  Biomarker discovery in mass spectral profiles by means of selectivity ratio plot , 2009 .

[19]  Chomtip Pornpanomchai,et al.  Image analysis based on color, shape and texture for rice seed (Oryza sativa L.) germination evaluation , 2017 .

[20]  D. Batista,et al.  Chemical profiling of Portuguese Pinus pinea L. nuts. , 2010, Journal of the science of food and agriculture.

[21]  M. Özcan,et al.  Is the Profile of Fatty Acids, Tocopherols, and Amino Acids Suitable to Differentiate Pinus armandii Suspicious to Be Responsible for the Pine Nut Syndrome from Other Pinus Species? , 2018, Chemistry & biodiversity.

[22]  C. Nergiz,et al.  Chemical composition and nutritive value of Pinus pinea L. seeds , 2004 .

[23]  Lianxing Gao,et al.  Discriminating and elimination of damaged soybean seeds based on image characteristics , 2015 .

[24]  Y. Heyden,et al.  Classification models for neocryptolepine derivatives as inhibitors of the β-haematin formation. , 2011, Analytica chimica acta.

[25]  İsmail Öztürk,et al.  Determination of size and shape features of walnut (Juglans regia L.) cultivars using image processing , 2012 .

[26]  Danilo Monarca,et al.  Near-infrared spectroscopy for detection of hailstorm damage on olive fruit , 2016 .

[27]  Manuel Melgosa,et al.  Ripeness estimation of grape berries and seeds by image analysis , 2012 .

[28]  F. Jessen,et al.  Species determination of pine nuts in commercial samples causing pine nut syndrome , 2014 .

[29]  M. Pardos,et al.  Enhanced tools for predicting annual stone pine (Pinus pinea L.) cone production at tree and forest scale in Inner Spain , 2016 .

[30]  R. Calama,et al.  Mediterranean Stone Pine: Botany and Horticulture , 2012 .

[31]  R. Sánchez-Cuesta,et al.  Discriminant analysis of Mediterranean pine nuts (Pinus pinea L.) from Chilean plantations by near infrared spectroscopy (NIRS) , 2017 .

[32]  Danilo Monarca,et al.  Real-Time Monitoring of Organic Carrot (var. Romance) During Hot-Air Drying Using Near-Infrared Spectroscopy , 2017, Food and Bioprocess Technology.

[33]  R. Massantini,et al.  Effect of alternative postharvest control treatments on the storability of 'Golden Delicious' apples. , 2013, Journal of the science of food and agriculture.

[34]  Da-Wen Sun,et al.  Computer vision technology for food quality evaluation , 2008 .

[35]  Danilo Monarca,et al.  Feasibility of Vis/NIR spectroscopy for detection of flaws in hazelnut kernels , 2013 .

[36]  M. Tigabu,et al.  Identification of seed sources and parents of Pinus sylvestris L. using visible–near infrared reflectance spectra and multivariate analysis , 2005, Trees.

[37]  Yan-Fu Kuo,et al.  Identifying rice grains using image analysis and sparse-representation-based classification , 2016, Comput. Electron. Agric..