Skip to main content
ARS Home » Northeast Area » Beltsville, Maryland (BARC) » Beltsville Agricultural Research Center » Environmental Microbial & Food Safety Laboratory » Research » Publications at this Location » Publication #324759
Title: Detection of cucumber green mottle mosaic virus-infected watermelon seeds using short wave infrared (SWIR) hyperspectral imaging system

Author
item LEE, HOONSOO - Chungnam National University
item Kim, Moon
item LIM, HYUN-SUB - Chungnam National University
item LEE, WANG-HEE - Chungnam National University
item CHO, BYOUNG-KWAN - Chungnam National University

Submitted to: Biosystems Engineering
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 5/31/2016
Publication Date: 6/15/2016
Citation: Lee, H., Kim, M.S., Lim, H., Lee, W., Cho, B. 2016. Detection of cucumber green mottle mosaic virus-infected watermelon seeds using short wave infrared (SWIR) hyperspectral imaging system. Biosystems Engineering. 148:138-147.

Interpretive Summary: In this investigation, a short-wave infrared (SWIR) hyperspectral imaging system was used as a rapid nondestructive detection tool to discriminate virus-infected watermelon seeds from healthy seeds. The imaging-based analyses demonstrated the classification accuracy for virus-infected watermelon seeds with approximately 83.3% accuracy. The imaging method provides beneficial information to produce seed growers and producers.

Technical Abstract: The cucurbit diseases caused by cucumber green mottle mosaic virus (CGMMV) have led to a serious problem to growers and seed producers because it is difficult to prevent spreading through causal agent of seeds. Conventional detection methods for infected seed such as a biological, serological, and molecular measurement are not practicable for measuring whole samples due to its time and cost intensive nature. For this reason, it is necessary to develop a rapid and non-destructive novel technique for detecting seeds infestation. Herein, short-wave infrared (SWIR) hyperspectral imaging system known as a rapid, accurate, and nondestructive detection tool has been used to discriminate virus-infected seeds from healthy seeds with constructing detection algorithms based on partial least square discriminant analysis (PLS-DA) and least square support vector machine (LS-SVM). The classification accuracy for virus-infected watermelon seeds were 83.3% with the best model, demonstrating the potentiality of SWIR hyperspectral imaging system for detecting virus-infected watermelon seeds.