Near-Infrared Hyperspectral Imaging Combined with Deep Learning to Identify Cotton Seed Varieties
Abstract
:1. Introduction
2. Results and Discussion
2.1. Spectral Profiles of Cotton Seeds
2.2. Analysis of PCA Score Images
2.3. Effective Wavelength Selection
2.4. Discriminant Models using Full Spectra and Effective Wavelengths
3. Materials and Methods
3.1. Sample Preparation
3.2. Hyperspectral Image Acquisition and Correction
3.3. Spectral Data Preprocessing and Extraction
3.4. Multivariate Analysis
3.4.1. Principal Component Analysis
3.4.2. Partial Least Squares Discriminant Analysis
3.4.3. Logistic Regression
3.4.4. Support Vector Machine
3.4.5. Deep Learning Methods
3.4.6. Effective Wavelength Selection
3.4.7. Model Evaluation and Software
4. Conclusions
Author Contributions
Funding
Conflicts of Interest
References
- Wendel, J.F.; Albert, V.A. Phylogenetics of the Cotton Genus (Gossypium): Character-State Weighted Parsimony Analysis of Chloroplast-DNA Restriction Site Data and Its Systematic and Biogeographic Implications. Syst. Botany 1992, 17, 115–143. [Google Scholar] [CrossRef]
- Vanisri, S.; Durga, R.; Swathi, G.; Jamal, M.; Sreedhar, M.; Kumar, N.R.; Ramprasad, E.; Raviteja, Y. DNA Fingerprinting for Identification of Rice Varieties and Seed Genetic Purity Assessment. Agric. Res. 2018, 7, 1–12. [Google Scholar] [CrossRef]
- Korir, N.K.; Han, J.; Shangguan, L.; Wang, C.; Kayesh, E.; Zhang, Y.; Fang, J. Plant variety and cultivar identification: advances and prospects. Crit. Rev. Biotechnol. 2013, 33, 111–125. [Google Scholar] [CrossRef] [PubMed]
- Amiryousefi, M.R.; Mohebbi, M.; Tehranifar, A. Pomegranate seed clustering by machine vision. Food Sci. Nutr. 2018, 6, 18–26. [Google Scholar] [CrossRef]
- Kurtulmuş, F.; Alibas, I.; Kavdir, I. Classification of pepper seeds using machine vision based on neural network. Int. J. Agric. Biol. Eng. 2015, 9, 51–62. [Google Scholar] [CrossRef]
- Feng, L.; Zhu, S.; Liu, F.; He, Y.; Bao, Y.; Zhang, C. Hyperspectral imaging for seed quality and safety inspection: A review. Plant Methods 2019, 15, 91. [Google Scholar] [CrossRef] [PubMed]
- Cui, Y.J.; Xu, L.J.; Dong, A.; Zhe, L.; Zhu, D.H. Identification of maize seed varieties based on near infrared reflectance spectroscopy and chemometrics. Int. J. Agric. Biol. Eng. 2018, 11, 177–183. [Google Scholar] [CrossRef]
- Jia, S.Q.; Dong, A.; Zhe, L.; Gu, J.C.; Li, S.M.; Zhang, X.D.; Zhu, D.H.; Guo, T.T.; Yan, Y.L. Variety identification method of coated maize seeds based on near- infrared spectroscopy and chemometrics. J. Cereal Sci. 2015, 63, 21–26. [Google Scholar] [CrossRef]
- Farhadi, M.; Tigabu, M.; Pietrzykowski, M.; Danusevičius, D.; Odén, P.C. Application of near infrared spectroscopy for authentication of Picea abies seed provenance. New Forests 2017, 48, 629–642. [Google Scholar] [CrossRef]
- Lorente, D.; Aleixos, N.; Gómez-Sanchis, J.; Cubero, S.; García-Navarrete, O.L.; Blasco, J. Recent Advances and Applications of Hyperspectral Imaging for Fruit and Vegetable Quality Assessment. Food Bioprocess Technol. 2012, 5, 1121–1142. [Google Scholar] [CrossRef]
- Bodner, G.; Nakhforoosh, A.; Arnold, T.; Leitner, D. Hyperspectral imaging: a novel approach for plant root phenotyping. Plant Methods 2018, 14, 84. [Google Scholar] [CrossRef] [PubMed]
- Gowen, A.A.; Feng, Y.; Gaston, E.; Valdramidis, V. Recent applications of hyperspectral imaging in microbiology. Talanta 2015, 137, 43–54. [Google Scholar] [CrossRef] [PubMed]
- Dong, X.C.; Jakobi, M.; Wang, S.J.; Köhler, M.H.; Zhang, X.X.; Koch, A.W. A review of hyperspectral imaging for nanoscale materials research. Appl. Spectrosc. Rev. 2018, 54, 285–305. [Google Scholar] [CrossRef]
- Mahesh, S.; Manickavasagan, A.; Jayas, D.S.; Paliwal, J.; White, N.D.G. Feasibility of near-infrared hyperspectral imaging to differentiate Canadian wheat classes. Biosyst. Eng. 2008, 101, 50–57. [Google Scholar] [CrossRef]
- Choudhary, R.; Mahesh, S.; Paliwal, J.; Jayas, D.S. Identification of wheat classes using wavelet features from near infrared hyperspectral images of bulk samples. Biosyst. Eng. 2009, 102, 115–127. [Google Scholar] [CrossRef]
- Sun, J.; Jiang, S.Y.; Mao, H.P.; Wu, X.H.; Li, Q.L. Classification of Black Beans Using Visible and Near Infrared Hyperspectral Imaging. Int. J. Food Propert. 2016, 19, 1687–1695. [Google Scholar] [CrossRef]
- Carreiro Soares, S.F.; Medeiros, E.P.; Pasquini, C.; de Lelis Morello, C.; Harrop Galv?o, R.K.; Ugulino Araújo, M.C. Classification of individual cotton seeds with respect to variety using near-infrared hyperspectral imaging. Anal. Methods 2016, 8, 8498–8505. [Google Scholar] [CrossRef]
- Yang, X.L.; Hong, H.M.; You, Z.H.; Cheng, F. Spectral and Image Integrated Analysis of Hyperspectral Data for Waxy Corn Seed Variety Classification. Sensors 2015, 15, 15578–15594. [Google Scholar] [CrossRef] [Green Version]
- Cheng, G.; Han, J.W. A survey on object detection in optical remote sensing images. ISPRS J. Photogramm. Remote Sens. 2016, 117, 11–28. [Google Scholar] [CrossRef] [Green Version]
- Shen, D.G.; Wu, G.R.; Suk, H.-I. Deep Learning in Medical Image Analysis. Annu. Rev. Biomed. Eng. 2017, 19, 221–248. [Google Scholar] [CrossRef] [Green Version]
- Kamilaris, A.; Prenafeta-Boldu, F.X. Deep learning in agriculture: A survey. Comput. Electron. Agric. 2018, 147, 70–90. [Google Scholar] [CrossRef] [Green Version]
- Hammad, I.; El-Sankary, K. Impact of Approximate Multipliers on VGG Deep Learning Network. IEEE Access 2018, 6, 60438–60444. [Google Scholar] [CrossRef]
- Jun, Y.H.; Taejoon, E.; Taeseong, K.; Hyungseob, S.; Dosik, H.; Hi, B.S.; Won, P.Y.; Ho-Joon, L.; Wook, C.B.; Soo, A.S. Deep-learned 3D black-blood imaging using automatic labelling technique and 3D convolutional neural networks for detecting metastatic brain tumors. Sci. Rep. 2018, 8, 9450. [Google Scholar] [CrossRef] [PubMed]
- Qiu, Z.J.; Jian, C.; Ying, Z.Y.; Su, Z.S.; Yong, H.; Chu, Z. Variety Identification of Single Rice Seed Using Hyperspectral Imaging Combined with Convolutional Neural Network. Appl. Sci. 2018, 8, 212. [Google Scholar] [CrossRef]
- Yushi Chen; Zhouhan Lin; Xing Zhao; Gang Wang; Yanfeng Gu Deep Learning-Based Classification of Hyperspectral Data. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 2017, 7, 2094–2107. [CrossRef]
- Feng, L.; Zhu, S.; Zhou, L.; Zhao, Y.; Bao, Y.; Zhang, C.; He, Y. Detection of Subtle Bruises on Winter Jujube Using Hyperspectral Imaging With Pixel-Wise Deep Learning Method. IEEE ACCESS 2019, 7, 64494–64505. [Google Scholar] [CrossRef]
- Yu, X.J.; Wang, J.P.; Wen, S.T.; Yang, J.Q.; Zhang, F.F. A deep learning based feature extraction method on hyperspectral images for nondestructive prediction of TVB-N content in Pacific white shrimp (Litopenaeus vannamei). Biosyst. Eng. 2019, 178, 244–255. [Google Scholar] [CrossRef]
- Khodabux, K.; L’Omelette, M.S.S.; Jhaumeer-Laulloo, S.; Ramasami, P.; Rondeau, P. Chemical and near-infrared determination of moisture, fat and protein in tuna fishes. Food Chem. 2007, 102, 669–675. [Google Scholar] [CrossRef]
- He, J.; Chen, L.D.; Chu, B.Q.; Zhang, C. Determination of total polysaccharides and total flavonoids in Chrysanthemum morifolium using near-infrared hyperspectral imaging and multivariate analysis. Molecules 2018, 23, 2395. [Google Scholar] [CrossRef]
- Feng, L.; Zhu, S.S.; Zhang, C.; Bao, Y.D.; Feng, X.P.; He, Y. Identification of Maize Kernel Vigor under Different Accelerated Aging Times Using Hyperspectral Imaging. Molecules 2018, 23, 3078. [Google Scholar] [CrossRef]
- Chuen, L.L.; Choong-Yeun, L.; Aziz, J.A. Partial Least Squares-Discriminant Analysis (PLS-DA) for classification of high-dimensional (HD) data: a review of contemporary practice strategies and knowledge gaps. Analyst 2018, 143, 3526–3539. [Google Scholar] [CrossRef]
- Wu, N.; Zhang, C.; Bai, X.; Du, X.; He, Y. Discrimination of Chrysanthemum Varieties Using Hyperspectral Imaging Combined with a Deep Convolutional Neural Network. Molecules 2018, 23, 2831. [Google Scholar] [CrossRef] [PubMed]
- Zhang, C.; Liu, F.; He, Y. Identification of coffee bean varieties using hyperspectral imaging: Influence of preprocessing methods and pixel-wise spectra analysis. Sci. Rep. 2018, 8, 2166. [Google Scholar] [CrossRef] [PubMed]
- Jiang, M.; Liang, Y.; Feng, X.; Fan, X.; Pei, Z.; Xue, Y.; Guan, R. Text classification based on deep belief network and softmax regression. Neural Comput. Appl. 2018, 29, 61–70. [Google Scholar] [CrossRef]
- Lu, Z.; Jiang, X.; Kot, A. Deep Coupled ResNet for Low-Resolution Face Recognition. IEEE Signal Process. Lett. 2018, 25, 526–530. [Google Scholar] [CrossRef]
- Zhang, C.; Guo, C.T.; Liu, F.; Kong, W.W.; Lou, B.G. Hyperspectral imaging analysis for ripeness evaluation of strawberry with support vector machine. J. Food Eng. 2016, 179, 11–18. [Google Scholar] [CrossRef]
Sample Availability: Samples of the compounds are available from the authors. |
Methods | No. | Effective Wavelengths (nm) |
---|---|---|
PCA loadings | 43 | 1009, 1025, 1032, 1052, 1069, 1082, 1096, 1116, 1119, 1123, 1126, 1130, 1200, 1204, 1224, 1227, 1230, 1241, 1264, 1268, 1308, 1315, 1318, 1321, 1342, 1345, 1362, 1386, 1396, 1399, 1402, 1409, 1426, 1443, 1450, 1453, 1456, 1470, 1548, 1554, 1588, 1598, 1602 |
Classifier | Full Spectra (%) | Effective Wavelengths (%) | ||||
---|---|---|---|---|---|---|
Calibration | Validation | Prediction | Calibration | Validation | Prediction | |
CNN-SoftMax a | 91.191 | 89.065 | 88.838 | 87.629 | 84.071 | 82.860 |
CNN-LR | 94.060 | 88.611 | 87.752 | 90.070 | 83.731 | 83.276 |
CNN-PLS-DA | 91.112 | 88.082 | 86.644 | 87.088 | 82.709 | 82.027 |
CNN-SVM | 93.695 | 89.255 | 88.006 | 89.970 | 84.487 | 84.260 |
ResNet-SoftMax | 95.381 | 85.698 | 86.039 | 92.273 | 79.985 | 79.228 |
ResNet-LR | 99.585 | 84.335 | 82.324 | 98.238 | 76.040 | 75.952 |
ResNet-PLS-DA | 95.130 | 85.585 | 85.358 | 91.707 | 78.509 | 77.677 |
ResNet-SVM | 96.325 | 85.963 | 85.887 | 94.098 | 79.153 | 79.115 |
LR | 84.156 | 82.406 | 83.012 | 62.736 | 62.429 | 65.305 |
PLS-DA | 81.764 | 79.947 | 80.401 | 78.870 | 77.261 | 77.147 |
SVM | 93.557 | 89.217 | 88.422 | 89.441 | 84.147 | 84.033 |
© 2019 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
Share and Cite
Zhu, S.; Zhou, L.; Gao, P.; Bao, Y.; He, Y.; Feng, L. Near-Infrared Hyperspectral Imaging Combined with Deep Learning to Identify Cotton Seed Varieties. Molecules 2019, 24, 3268. https://doi.org/10.3390/molecules24183268
Zhu S, Zhou L, Gao P, Bao Y, He Y, Feng L. Near-Infrared Hyperspectral Imaging Combined with Deep Learning to Identify Cotton Seed Varieties. Molecules. 2019; 24(18):3268. https://doi.org/10.3390/molecules24183268
Chicago/Turabian StyleZhu, Susu, Lei Zhou, Pan Gao, Yidan Bao, Yong He, and Lei Feng. 2019. "Near-Infrared Hyperspectral Imaging Combined with Deep Learning to Identify Cotton Seed Varieties" Molecules 24, no. 18: 3268. https://doi.org/10.3390/molecules24183268