Seed variety purity is the main indicator of seed quality, which affects crop yield and product quality. In the present study, a new method for the identification of pine nut varieties based on hyperspectral imaging and convolutional neural networks LeNet-5 was established so as to avoid the hybridization of different varieties of pine nuts, improve the identification efficiency and reduce the cost of identification. Images of 128 wavelengths in the 370–1042 nm range were acquired by hyperspectral imaging. The spectrum and image of each seed were obtained by means of black-and-white correction and region segmentation of the original image. Twenty characteristic wavelengths were extracted from the first three principal components (PCs) of principal component analysis (PCA). A support vector machine (SVM) spectral recognition model based on full wavelengths and characteristic wavelengths was established. For different species of pine seeds, the classification accuracies of the prediction set in the aforementioned datasets were 97.7 and 93.1%, respectively. The seed images of 20 characteristic wavelengths were input into LeNet-5 to improve the network structure and the number of convolution channels. The improved LeNet-5 performed better with over 99% accuracy. Such results show that the convolutional neural network is of considerable significance for fast and nondestructive identification of pine seed varieties.
Similar content being viewed by others
References
R. Florin, Biol. Rev., 29, No. 4, 367–389 (2010).
M. Hizume, Natural Sci., 8, 1–108 (1988).
L. Linchu, Guangxi Plants, 324–328 (1988).
J. G. Niemann, Acta Bot. Neerl., 28, 73–88 (1979).
R. A. Price, J. Olsen-Stojkovich, and J. M. Lowenstein, Syst. Bot., 12, 91–97 (1987).
A. Guri, P. Kefalas, and V. Roussis, Phytother. Res., 20, 263–266 (2006).
G. Dong, J. Guo, C. Wang, Z. L. Chen, and D. Z. Zhu, Spectrosc. Spectr. Anal., 35, Article ID 3369 (2015).
J. Zhang, L. M. Dai, and F. Cheng, Molecules, 24, 25 (2019).
P. Yuan, L. Pang, L. M. Wang, and L. Yan, Int. Food Res. J., 29, No. 2, 397–405 (2022).
I. Baek, M. S. Kim, B. K. Cho, C. Mo, J. Y. Barnaby, A. M. McClung, and M. Oh, Appl. Sci. (Basel), 9, No. 5, Article ID 1027 (2019).
D. W. Sun, H. Y. Cen, H. Y. Weng, L. Wan, A. Abdalla, A. I. El-Manawy, Y. M. Zhu, N. Zhao, H. W. Fu, J. Tang, X. L. Li, H. K. Zheng, Q. Y. Shu, F. Liu, and Y. He, Plant Methods, 15, 16 (2019).
Y. D. Bao, C. X. Mi, N. Wu, F. Liu, and Y. He, Appl. Sci. (Basel), 9, No. 19, Article ID 4119 (2019).
S. S. Zhu, L. Zhou, P. Gao, Y. D. Bao, Y. He, and L. Feng, Molecules, 24, 17 (2019).
M. B. McDonald, Seed Sci. Res., 8, 265–275 (1998).
J. S. C. Smith and J. C. Register, Seed Sci. Res., 8, 285–293 (1998).
Z. Chaoliang and W. Bin, Crop Mag., 1, 13–16 (1998).
Q. Zhu, Z. Feng, M. Huang, and X. Zhu, Trans. Chin. Soc. Agric. Eng., 28, 271–276 (2012).
S. Javanmardi, S. H. M. Ashtiani, F. J. Verbeek, and A. Martynenko, J. Stored Prod. Res., 92 (2021).
A. Krizhevsky, I. Sutskever, and G. E. Hinton, Commun. ACM, 60, 84–90 (2017).
Y. LeCun, Y. Bengio, and G. Hinton, Nature, 521, 436–444 (2015).
L. B. Wang, J. Y. Liu, J. Zhang, J. Wang, and X. F. Fan, Front. Plant Sci., 13, 168–174 (2022).
W. Lu, R. T. Du, P. S. Niu, G. N. Xing, H. Luo, Y. M. Deng, and L. Shu, Front. Plant Sci., 12, Article ID 791256 (2022).
H. Li, L. Zhang, H. Sun, Z. H. Rao, and H. Y. Ji, J. Food Proc. Eng., 44, Article ID e13767 (2021).
G. Y. Zhao, L. Z. Quan, H. L. Li, H. Q. Feng, S. W. Li, S. H. Zhang, and R. Q. Liu, Comput. Electron. Agric., 187, Article ID 106230 (2021).
N. Otsu, IEEE Trans. Syst. Man Cybern., 9, 62–66 (1979).
A. Femenias, M. B. Bainotti, F. Gatius, A. J. Ramos, and S. Marin, Food Res. Int., 139, Article ID 109925 (2021).
B. Hasanzadeh, Y. Abbaspour-Gilandeh, A. Soltani-Nazarloo, M. Hernandez-Hernandez, I. Gallardo-Bernal, and J. L. Hernandez-Hernandez, Horticulturae, 8, 598 (2022).
M. Gabrielli, V. Lancon-Verdier, P. Picouet, and C. Maury, Chemosensors, 9, 71 (2021).
R. J. Barnes, M. S. Dhanoa, Susan, and J. Lister, Appl. Spectrosc., 43, 772–777 (1989).
K. Pearson, Philos. Mag., 2, Ser 6, no. 11, 559–572 (1901).
D. Liu, J. Ma, D. W. Sun, H. Pu, W. Gao, J. Qu, and X. A. Zeng, Food Bioproc. Technol., 7, 3100–3108 (2014).
J. Platt, Tech. Rep., 98, 14 (1998).
G. Mountrakis, J. Im, and C. Ogole, ISPRS J. Photogram. Remote Sens., 66, 247–259 (2011).
K. Were, D. T. Bui, Ø. B. Dick, and B. R. Singh, Ecol. Indic., 52, 394–403 (2015).
V. Rodriguez-Galiano, M. Sanchez-Castillo, M. Chica-Olmo, and M. Chica-Rivas, Ore Geol. Rev., 71, 804–818 (2015).
C. Cortes and V. Vapnik, Mach. Learn., 20, 273–297 (1995).
Y. Lecun and L. Bottou, Proc. IEEE, 86, 2278–2324 (1998).
X. Zhang, L. Z. Zhou, and L. L. Zhang, Computer and Modernization, 5655–5660 (2019).
Author information
Authors and Affiliations
Corresponding author
Additional information
Abstract of article is published in Zhurnal Prikladnoi Spektroskopii, Vol. 90, No. 4, p. 660, July–August, 2023.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Ma, J., Pang, L., Guo, Y. et al. Application of Hyperspectral Imaging to Identify Pine Seed Varieties. J Appl Spectrosc 90, 916–923 (2023). https://doi.org/10.1007/s10812-023-01614-7
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10812-023-01614-7