iBet uBet web content aggregator. Adding the entire web to your favor.
iBet uBet web content aggregator. Adding the entire web to your favor.



Link to original content: http://www.ncbi.nlm.nih.gov/pubmed/29958467
Potential of Visible and Near-Infrared Hyperspectral Imaging for Detection of Diaphania pyloalis Larvae and Damage on Mulberry Leaves - PubMed Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2018 Jun 28;18(7):2077.
doi: 10.3390/s18072077.

Potential of Visible and Near-Infrared Hyperspectral Imaging for Detection of Diaphania pyloalis Larvae and Damage on Mulberry Leaves

Lingxia Huang  1   2 , Liang Yang  3 , Liuwei Meng  4 , Jingyu Wang  5 , Shaojia Li  6   7   8 , Xiaping Fu  9 , Xiaoqiang Du  10   11 , Di Wu  12   13   14
Affiliations

Potential of Visible and Near-Infrared Hyperspectral Imaging for Detection of Diaphania pyloalis Larvae and Damage on Mulberry Leaves

Lingxia Huang et al. Sensors (Basel). .

Abstract

Mulberry trees are an important crop for sericulture. Pests can affect the yield and quality of mulberry leaves. This study aims to develop a hyperspectral imaging system in visible and near-infrared (NIR) region (400⁻1700 nm) for the rapid identification of Diaphania pyloalis larvae and its damage. The extracted spectra of five region of interests (ROI), namely leaf vein, healthy mesophyll, slight damage, serious damage, and Diaphania pyloalis larva at 400⁻1000 nm (visible range) and 900⁻1700 nm (NIR range), were used to establish a partial least squares discriminant analysis (PLS-DA) and least-squares support vector machines (LS-SVM) models. Successive projections algorithm (SPA), uninformation variable elimination (UVE), UVE-SPA, and competitive adaptive reweighted sampling were used for variable selection. The best models in distinguishing between leaf vein, healthy mesophyll, slight damage and serious damage, leaf vein, healthy mesophyll, and larva, slight damage, serious damage, and larva were all the SPA-LS-SVM models, based on the NIR range data, and their correct rate of prediction (CRP) were all 100.00%. The best model for the identification of all five ROIs was the UVE-SPA-LS-SVM model, based on visible range data, which had the CRP value of 97.30%. In summary, visible and near infrared hyperspectral imaging could distinguish Diaphania pyloalis larvae and their damage from leaf vein and healthy mesophyll in a rapid and non-destructive way.

Keywords: Diaphania pyloalis; damage; hyperspectral imaging; larvae; mulberry leaves.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure 1
Figure 1
Extracted mean representative spectra and images of leaf vein, healthy mesophyll, slight damage, serious damage, and Diaphania pyloalis larva: (a) 400–1000 nm (visible range) and (b) 900–1700 nm (near-infrared [NIR] range); (c) 660 nm and (d) 1250 nm.
Figure 1
Figure 1
Extracted mean representative spectra and images of leaf vein, healthy mesophyll, slight damage, serious damage, and Diaphania pyloalis larva: (a) 400–1000 nm (visible range) and (b) 900–1700 nm (near-infrared [NIR] range); (c) 660 nm and (d) 1250 nm.
Figure 2
Figure 2
Score plot of the first two principal components of Classification I to IV based on visible range data and NIR range data. Classification I: (a) visible range (400–1000 nm) and (b) NIR range (900–1700 nm). Classification II: (c) visible range (400–1000 nm) and (d) NIR range (900–1700 nm). Classification III: (e) visible range (400–1000 nm) and (f) NIR range (900–1700 nm). Classification IV: (g) visible range (400–1000 nm) and (h) NIR range (900–1700 nm).
Figure 2
Figure 2
Score plot of the first two principal components of Classification I to IV based on visible range data and NIR range data. Classification I: (a) visible range (400–1000 nm) and (b) NIR range (900–1700 nm). Classification II: (c) visible range (400–1000 nm) and (d) NIR range (900–1700 nm). Classification III: (e) visible range (400–1000 nm) and (f) NIR range (900–1700 nm). Classification IV: (g) visible range (400–1000 nm) and (h) NIR range (900–1700 nm).
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

References

    1. Goldsmith M.R., Shimada T., Abe H. The genetics and genomics of the silkworm, Bombyx mori. Annu. Rev. Entomol. 2005;50:71–100. doi: 10.1146/annurev.ento.50.071803.130456. - DOI - PubMed
    1. Department of Market Operation and Consumption Promotion (National Cocoon and Silk Coordination Office), Ministry of Commerce of the People’s Republic of China Operation Profiles of Cocoon and Silk Industry in 2017. [(accessed on 28 March 2018)]; Available online: http://scyxs.mofcom.gov.cn/article/c/201803/20180302724737.shtml.
    1. Zhu B.J., Liu Q.N., Dai L.S., Wang L., Sun Y., Lin K.Z., Wei G.Q., Liu C.L. Characterization of the complete mitochondrial genome of Diaphania pyloalis (lepidoptera: Pyralididae) Gene. 2013;527:283–291. doi: 10.1016/j.gene.2013.06.035. - DOI - PubMed
    1. Zhao X.H., Bai X.C., Shi G.F. Research progress on outbreak regularity of mulberry moth and control techniques. Bull. Sericult. 2013;44:5–10.
    1. Liu T., Chen W., Wu W., Sun C., Guo W., Zhu X. Detection of aphids in wheat fields using a computer vision technique. Biosyst. Eng. 2016;141:82–93. doi: 10.1016/j.biosystemseng.2015.11.005. - DOI