Pine nut species recognition using NIR spectroscopy and image analysis

Moscetti, Roberto; Berhe, Daniel Hagos; Agrimi, Mariagrazia; Haff, Ron P.; Liang, Pei‐Shih; Ferri, Serena; Monarca, Danilo; Massantini, Riccardo

doi:10.1016/j.jfoodeng.2020.110357

Cited by 18 publications

(22 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…1 ). These bands were found to be associated with proteins, amino acids, moisture, lipids and carbohydrates in previous studies 20 , 22 . Notably, our results also showed that three sensitive bands (1,147–1,154 nm, 1,907–1,927 nm, 2,227–2,254 nm) in these regions (1,111–2,500 nm) have great influence on the model accuracy based on sliding window method (Fig.…”

Section: Discussionsupporting

confidence: 52%

“…Loewe et al 21 collected NIR spectral data of Mediterranean Pinus pinea from Chilean plantations for classification. Moscetti et al 22 collected the NIR spectral data of the nuts of P. pinea and Pinus sibirica in different regions and established a spectral classification model by using PLS-DA and Interval PLS-DA (IPLS-DA) methods. However, the effects of other different classification models still need to be further discussed in more species of pine nuts.…”

Section: Introductionmentioning

confidence: 99%

“…Deep convolutional neural network (CNN) has been successfully applied in image recognition for applications such as tomato pesto recognition 25 , fish image recognition 26 . Moscetti et al 22 collected the image data of the nuts of P. pinea and P. sibirica in different regions, carried out feature extraction, obtained 10 features based on image data, and used these features to construct image-based classification model. Although the feasibility of pine nuts classification has been proved based on manually extracted image-features, the automatic classification model is still worthy of further research in more species of pine nuts.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Applications of machine learning in pine nuts classification

Huang

Liu

Jiao

et al. 2022

Sci Rep

View full text Add to dashboard Cite

Pine nuts are not only the important agent of pine reproduction and afforestation, but also the commonly consumed nut with high nutritive values. However, it is difficult to distinguish among pine nuts due to the morphological similarity among species. Therefore, it is important to improve the quality of pine nuts and solve the adulteration problem quickly and non-destructively. In this study, seven pine nuts (Pinus bungeana, Pinus yunnanensis, Pinus thunbergii, Pinus armandii, Pinus massoniana, Pinus elliottii and Pinus taiwanensis) were used as study species. 210 near-infrared (NIR) spectra were collected from the seven species of pine nuts, five machine learning methods (Decision Tree (DT), Random Forest (RF), Multilayer Perceptron (MLP), Support Vector Machine (SVM) and Naive Bayes (NB)) were used to identify species of pine nuts. 303 images were used to collect morphological data to construct a classification model based on five convolutional neural network (CNN) models (VGG16, VGG19, Xception, InceptionV3 and ResNet50). The experimental results of NIR spectroscopy show the best classification model is MLP and the accuracy is closed to 0.99. Another experimental result of images shows the best classification model is InceptionV3 and the accuracy is closed to 0.964. Four important range of wavebands, 951–957 nm, 1,147–1,154 nm, 1,907–1,927 nm, 2,227–2,254 nm, were found to be highly related to the classification of pine nuts. This study shows that machine learning is effective for the classification of pine nuts, providing solutions and scientific methods for rapid, non-destructive and accurate classification of different species of pine nuts.

show abstract

Section: Discussionsupporting

confidence: 52%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Applications of machine learning in pine nuts classification

Huang

Liu

Jiao

et al. 2022

Sci Rep

View full text Add to dashboard Cite

show abstract

“…However, this technique is only effective in identifying samples with apparent appearance characteristics, and cannot be used to distinguish the internal differences of samples. As an internal detection technique, near-infrared spectroscopy (NIRS) has been widely used to identify the geographical and botanical origin of agricultural products [13], particularly nuts, e.g., hazelnut [14][15][16], macadamia nut [17], walnut [18,19], and pine nut [20]. However, NIRS cannot obtain the information in the whole sample space due to single-point detection [21].…”

Section: Introductionmentioning

confidence: 99%

“…Funding: This work was funded by Jiangsu Agriculture Science and Technology Innovation Fund, grant number CX (20)…”

mentioning

confidence: 99%

Identification of Geographical Origin of Chinese Chestnuts Using Hyperspectral Imaging with 1D-CNN Algorithm

Jiang

et al. 2021

Agriculture

View full text Add to dashboard Cite

The adulteration in Chinese chestnuts affects the quality, taste, and brand value. The objective of this study was to explore the feasibility of the hyperspectral imaging (HSI) technique to determine the geographical origin of Chinese chestnuts. An HSI system in spectral range of 400–1000 nm was applied to identify a total of 417 Chinese chestnuts from three different geographical origins. Principal component analysis (PCA) was preliminarily used to investigate the differences of average spectra of the samples from different geographical origins. A deep-learning-based model (1D-CNN, one-dimensional convolutional neural network) was developed first, and then the model based on full spectra and optimal wavelengths were established for various machine learning methods, including partial least squares-discriminant analysis (PLS-DA) and particle swarm optimization-support vector machine (PSO-SVM). The optimal results based on full spectra for 1D-CNN, PLS-DA, and PSO-SVM models were 97.12%, 97.12%, and 95.68%, respectively. Competitive adaptive reweighted sampling (CARS) and a successive projections algorithm (SPA) were individually utilized for wavelengths selection, and the results of simplified models generally improved. The contrasting results demonstrated that the prediction accuracies of SPA-PLS-DA and 1D-CNN both reached 97.12%, but 1D-CNN presented a higher Kappa coefficient value than SPA-PLS-DA. Meanwhile, the sensitivities and specificities of SPA-PLS-DA and 1D-CNN models were both above 90% for the samples from each geographical origin. These results indicated that both SPA-PLS-DA and 1D-CNN models combined with HSI have great potential for the geographical origin identification of Chinese chestnuts.

show abstract