Abstract
Citrus fruit granulation is a major physical disorder during late maturity and post-harvest storage, and it greatly undermines the quality of fruit. Currently, there is still a lack of rapid and nondestructive methods to detect citrus granulation. This study proposes a nondestructive granulation detecting method based on deep learning. Different models were established with the input of preprocessed transmission spectra obtained by hyperspectral imaging. Conventional convolution neural network (CNN) got the best accuracy at 88.02% for training, compared with the least-square support vector machine (LS-SVM) and back-propagation neural network (BP-NN). After adding the batch-normalization layer to the CNN, the experimental results show that the detection model obtained a 100% accuracy in train set and 97.9% in validation set, respectively. And then, through analyzing the well-trained model layer by layer, bands of 660.2–721.1 nm, 708.5–750 nm and 806.5–847 nm were the spectra greatly related to granulation. The model rebuilt with these feature bands obtained 90.1% and 85.4% accuracy in train set and validation set, respectively. This way, effective wavelength selection can find bands highly correlated with granulation.Combined with some research on functional group, it is possible that inference to internal matter changes in granulation process, which may provide some hints to explore the reason of granulation. It is also meaningful to develop granulation-detecting equipment for citrus fruits.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Arendse E, Fawole O, Magwaza L, Opara U (2017) Non-destructive prediction of internal and external quality attributes of fruit with thick rind: a review. J Food Eng 217:11–23. https://doi.org/10.1016/j.jfoodeng.2017.08.009
Awasthi RP, Nauriyal JP (1972) Studies on granulation in sweet orange. II. Differences in moisture, total soluble solids and ascorbic acid of juice vesicles in different stages of granulation. Punjab Hort J 12:203–211
Badaro AT, Garcia-Martin JF, Lopez-Barrera MDC, Barbin DF, Alvarez-Mateos P (2020) Determination of pectin content in orange peels by near infrared hyperspectral imaging. Food Chem 323:126861. https://doi.org/10.1016/j.foodchem.2020.126861
Catalano J, Di Tullio V, Wagner M, Zumbulyadis N, Centeno SA, Dybowski C (2020) Review of the use of NMR spectroscopy to investigate structure, reactivity, and dynamics of lead soap formation in paintings. Magn Reson Chem. https://doi.org/10.1002/mrc.5025
Chakrawar VR, Singh R, Subbaih BV (1980) Studies on citrus granulation III Sugar transport and fruit granulation in citrus. Haryana J Hortic Sci 9:17–20
Chen YY, Wang ZB (2019) End-to-end quantitative analysis modeling of near-infrared spectroscopy based on convolutional neural network. J Chemometr 33. https://doi.org/10.1002/cem.3122
Chen H, Qiao H, Lin B, Xu G, Tang G, Cai K (2019) Study of modeling optimization for hyperspectral imaging quantitative determination of naringin content in pomelo peel. Comput Electron Agric 157:410–416. https://doi.org/10.1016/j.compag.2019.01.013
Elmasry G, Nakauchi S (2016) Image analysis operations applied to hyperspectral images for non-invasive sensing of food quality – a comprehensive review. Biosyst Eng 142:53–82. https://doi.org/10.1016/j.biosystemseng.2015.11.009
Feng YZ, Sun DW (2012) Application of hyperspectral imaging in food safety inspection and control: a review. Crit Rev Food Sci Nutr 52:1039–1058. https://doi.org/10.1080/10408398.2011.651542
Feng J, Chen J, Liu L, Cao X, Zhang X, Jiao L, Yu T (2019) CNN-based multilayer spatial–spectral feature fusion and sample augmentation with local and nonlocal constraints for hyperspectral image classification. IEEE J-STARS, pp 1–15. https://doi.org/10.1109/JSTARS.2019.2900705
Kong Y, Wang X (2018) Spectral–spatial feature extraction for HSI classification based on supervised hypergraph and sample expanded CNN. IEEE J-STARS, pp 1–13. https://doi.org/10.1109/JSTARS.2018.2869210
Krizhevsky A, Sutskever I, Hinton G (2012) ImageNet classification with deep convolutional neural networks. NIPS 25:84–90. https://doi.org/10.1145/3065386
Lecun Y, Boser B, Denker J, Henderson D, Howard R, Hubbard WE, Jackel L (1989) Backpropagation applied to handwritten zip code recognition. Neural Comput 1:541–551. https://doi.org/10.1162/neco.1989.1.4.541
Lecun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proc IEEE 86:2278–2324. https://doi.org/10.1109/5.726791
Li J, Huang W, Tian X, Wang C, Fan S, Zhao C (2016) Fast detection and visualization of early decay in citrus using Vis-NIR hyperspectral imaging. Comput Electron Agric 127:582–592. https://doi.org/10.1016/j.compag.2016.07.016
Li M, Li B, Zhang W (2018) Rapid and non-invasive detection and imaging of the hydrocolloid-injected prawns with low-field NMR and MRI. Food Chem 242:16–21. https://doi.org/10.1016/j.foodchem.2017.08.086
Magwaza LS, Opara UL, Nieuwoudt H, Cronje PJR, Saeys W, Nicolaï B (2011) NIR spectroscopy applications for internal and external quality analysis of citrus fruit—a review. Food Bioprocess Technol 5:425–444. https://doi.org/10.1007/s11947-011-0697-1
Malek S, Melgani F, Bazi Y (2017) One-dimensional convolutional neural networks for spectroscopic signal regression. J Chemom 32. https://doi.org/10.1002/cem.2977
Munshi SK, Singh R, Jawanda JS, Vij VK (1978) Studies on granulation in dancy tangerine (Citrus tangerina Tanaka) in relation to various quality attributes [India]. Indian J Hortic 35:85–90
Novikov DS, Fieremans E, Jespersen SN, Kiselev VG (2019) Quantifying brain microstructure with diffusion MRI: theory and parameter estimation. NMR Biomed 32:e3998. https://doi.org/10.1002/nbm.3998
Osborne BG (2006) Near-infrared spectroscopy in food analysis. Encycl Anal Chem. https://doi.org/10.1002/9780470027318.a1018
Picon A, Alvarez-Gila A, Seitz M, Ortiz-Barredo A, Echazarra J, Johannes A (2019) Deep convolutional neural networks for mobile capture device-based crop disease classification in the wild. Comput Electron Agric 161:280–290. https://doi.org/10.1016/j.compag.2018.04.002
Pu H, Lin L, Sun DW (2019) Principles of hyperspectral microscope imaging techniques and their applications in food quality and safety detection: a review. Compr Rev Food Sci Food Saf 18:853–866. https://doi.org/10.1111/1541-4337.12432
Qin J, Burks T, Ritenour M, Bonn W (2009) Detection of citrus canker using hyperspectral reflectance imaging with spectral information divergence. J Food Eng 93:183–191. https://doi.org/10.1016/j.jfoodeng.2009.01.014
Qin J, Burks T, Zhao X, Niphadkar N, Ritenour M (2011) Multispectral detection of citrus canker using hyperspectral band selection. T ASABE 54:2331–2341. https://doi.org/10.13031/2013.40643
Ren S, He K, Girshick R, Sun J (2015) Faster R-CNN: towards real-time object detection with region proposal networks. IEEE T Pattern Anal 39:1137–1149. https://doi.org/10.1109/TPAMI.2016.2577031
Ritenour M, Albrigo G, Burns JK, Miller WM (2004) Granulation in Florida citrus. Proc Florida State Hortic Soc 117:358–361
Sharma RR, Saxena SK (2004) Rootstocks influence granulation in Kinnow mandarin. Sci Hortic-Amsterdam 101:235–242. https://doi.org/10.1016/j.scienta.2003.10.010
Sharma RR, Singh R, Saxena SK (2006) Characteristics of citrus fruits in relation to granulation. Sci Hortic-Amsterdam 111:91–96. https://doi.org/10.1016/j.scienta.2006.09.007
Shi X, Zhong J, Liu C, Liu F, Zhang D (2018) Deep learning method for hyperspectral remote sensing images with small samples. Xitong Fangzhen Xuebao/J Syst Simul 30:2744–2752. https://doi.org/10.16182/j.issn1004731x.joss.201807039
Singh R (2001) 65-year research on citrus granulation. Ind J Hortic 58:112–144
Sladojevic S, Arsenovic M, Anderla A, Culibrk D, Stefanovic D (2016) Deep neural networks based recognition of plant diseases by leaf image classification. Comput Intell Neurosci 2016:3289801–3289811. https://doi.org/10.1155/2016/3289801
Sonego L, Ben-Arie R, Raynal J, Pech J-C (1995) Biochemical and physical evaluation of textural characteristics of nectarines exhibiting woolly breakdown: NMR imaging, X-ray computed tomography and pectin composition. Postharvest Biol Technol 5:187–198. https://doi.org/10.1016/0925-5214(94)00026-O
Srivastava V, Biswas B (2019) CNN-based salient features in HSI image semantic target prediction. Connect Sci 1–19. https://doi.org/10.1080/09540091.2019.1650330
Sullivan J, Twardowski M, Zaneveld J, Moore C, Barnard A, Donaghay P, Rhoades B (2006) Hyperspectral temperature and salt dependencies of absorption by water and heavy water in the 400-750 nm spectral range. Appl Opt 45:5294–5309. https://doi.org/10.1364/AO.45.005294
Theanjumpol P, Wongzeewasakun K, Muenmanee N, Wongsaipun S, Krongchai C, Changrue V, Boonyakiat D, Kittiwachana S (2019) Non-destructive identification and estimation of granulation in ‘Sai Num Pung’ tangerine fruit using near infrared spectroscopy and chemometrics. Postharvest Biol Technol 153:13–20. https://doi.org/10.1016/j.postharvbio.2019.03.009
Tian X, Fan S, Huang W, Wang Z, Li J (2019) Detection of early decay on citrus using hyperspectral transmittance imaging technology coupled with principal component analysis and improved watershed segmentation algorithms. Postharvest Biol Technol 161:111071. https://doi.org/10.1016/j.postharvbio.2019.111071
Viana OH, Mercante E, Felipetto H, Kusminski D, Bleil HG Jr (2017) Characterisation of the spectral-temporal pattern of the crambe crop using hyperspectral sensors. J Agric Sci-Cambridge 9:220. https://doi.org/10.5539/jas.v9n11p220
Wang XY, Wang P, Qi YP, Zhou CP, Yang LT, Liao XY, Wang LQ, Zhu DH, Chen LS (2014) Effects of granulation on organic acid metabolism and its relation to mineral elements in Citrus grandis juice sacs. Food Chem 145:984–990. https://doi.org/10.1016/j.foodchem.2013.09.021
Wang N-N, Sun D-W, Yang Y-C, Pu H, Zhu Z (2015) Recent advances in the application of hyperspectral imaging for evaluating fruit quality. Food Anal Method 9:178–191. https://doi.org/10.1007/s12161-015-0153-3
Yu X, Lu H, Wu D (2018) Development of deep learning method for predicting firmness and soluble solid content of postharvest Korla fragrant pear using Vis/NIR hyperspectral reflectance imaging. Postharvest Biol Technol 141:39–49. https://doi.org/10.1016/j.postharvbio.2018.02.013
Zhang H, Li Y, Zhang Y, Shen Q (2017) Spectral-spatial classification of hyperspectral imagery using a dual-channel convolutional neural network. Remote Sens Lett 8:438–447. https://doi.org/10.1080/2150704x.2017.1280200
Zhou F, Hang R, Liu Q, Yuan X (2019) Pyramid fully convolutional network for hyperspectral and multispectral image fusion. IEEE J-Stars 12:1549–1558. https://doi.org/10.1109/jstars.2019.2910990
Funding
This study was funded by the National Natural Science Foundation of China (NO. 61705037), the project of Gaoyuan Agricultural Engineering of Fujian (NO. 712018014), and the National Agricultural (Citrus) Industry Technology System Special Program (CARS-26-01A).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of Interest
The authors declare that they have no conflict of interest.
Human and Animal Rights
Not applicable.
Informed Consent
Not applicable.
Additional information
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Jie, D., Wu, S., Wang, P. et al. Research on Citrus grandis Granulation Determination Based on Hyperspectral Imaging through Deep Learning. Food Anal. Methods 14, 280–289 (2021). https://doi.org/10.1007/s12161-020-01873-6
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12161-020-01873-6