Next Article in Journal
Tunable Synthesis of Hollow Co3O4 Nanoboxes and Their Application in Supercapacitors
Next Article in Special Issue
Zebrafish Larvae Phenotype Classification from Bright-field Microscopic Images Using a Two-Tier Deep-Learning Pipeline
Previous Article in Journal
Opto-Electronic Refractometric Sensor Based on Surface Plasmon Resonances and the Bolometric Effect
Previous Article in Special Issue
An Effective Optimization Method for Machine Learning Based on ADAM
Open AccessFeature PaperArticle

Detecting Green Mold Pathogens on Lemons Using Hyperspectral Images

1
Public Safety Research Center, Konyang University, Nonsan 32992, Korea
2
Department of Civil Engineering, Konyang University, Nonsan 32992, Korea
3
Department of Bio-IT Engineering, Konyang University, Nonsan 32992, Korea
4
Linguistics for Sciences Department, Chernivtsi University, 58012 Chernivtsi, Ukraine
*
Author to whom correspondence should be addressed.
Appl. Sci. 2020, 10(4), 1209; https://doi.org/10.3390/app10041209
Received: 19 December 2019 / Revised: 30 January 2020 / Accepted: 6 February 2020 / Published: 11 February 2020
(This article belongs to the Special Issue Intelligent Processing on Image and Optical Information)
Hyperspectral images in the spectral wavelength range of 500 nm to 650 nm are used to detect green mold pathogens, which are parasitic on the surface of lemons. The images reveal that the spectral range of 500 nm to 560 nm is appropriate for detecting the early stage of development of the pathogen in the lemon, because the spectral intensity is proportional to the infection degree. Within the range, it was found that the dominant spectral wavelengths of the fresh lemon and the green mold pathogen are 580 nm and 550 nm, respectively, with the 550 nm being the most sensitive in detecting the pathogen with spectral imaging. The spectral intensity ratio of the infected lemon to the fresh one in the spectral range of 500 nm to 560 nm increases with the increasing degree of the infection. Therefore, the ratio can be used to effectively estimate the degree of lemons infecting by the green mold pathogens. It also shows that the sudden decrease of the spectral intensity corresponding to the dominant spectral wavelength of the fresh lemon, together with the neighboring spectral wavelengths can be used to classify fresh and contaminated lemons. The spectral intensity ratio of discriminating the fresh lemon from the infected one is calculated as 1.15. View Full-Text
Keywords: healthy and infected lemons; Hyperspectral image; Penicillium digitatum pathogen; lemon skin; dominant spectral wavelength; spectral intensity ratio healthy and infected lemons; Hyperspectral image; Penicillium digitatum pathogen; lemon skin; dominant spectral wavelength; spectral intensity ratio
Show Figures

Figure 1

MDPI and ACS Style

Vashpanov, Y.; Heo, G.; Kim, Y.; Venkel, T.; Son, J.-Y. Detecting Green Mold Pathogens on Lemons Using Hyperspectral Images. Appl. Sci. 2020, 10, 1209.

AMA Style

Vashpanov Y, Heo G, Kim Y, Venkel T, Son J-Y. Detecting Green Mold Pathogens on Lemons Using Hyperspectral Images. Applied Sciences. 2020; 10(4):1209.

Chicago/Turabian Style

Vashpanov, Yuriy; Heo, Gwanghee; Kim, Yongsuk; Venkel, Tetiana; Son, Jung-Young. 2020. "Detecting Green Mold Pathogens on Lemons Using Hyperspectral Images" Appl. Sci. 10, no. 4: 1209.

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop