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 #310215

Title: Multispectral fluorescence imaging technique for discrimination of cucumber (Cucumis Sativus) seed viability

Author
item MO, CHANGYEUN - Rural Development Administration - Korea
item Kim, Moon
item LIM, JONGKUK - Rural Development Administration - Korea
item CHO, BYOUNG-KWAN - Chungnam National University
item LEE, KANGJIN - Rural Development Administration - Korea
item KIM, GIYOUNG - Rural Development Administration - Korea

Submitted to: Transactions of the ASABE
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 5/15/2015
Publication Date: 8/17/2015
Citation: Mo, C., Kim, M.S., Lim, J., Cho, B., Lee, K., Kim, G. 2015. Multispectral fluorescence imaging technique for discrimination of cucumber (Cucumis Sativus) seed viability. Transactions of the ASABE. 58(4):959-968.

Interpretive Summary: We developed a nondestructive method for discriminating viable from non-viable cucumber seeds based on hyperspectral fluorescence imaging. The fluorescence spectra of cucumber seeds in the 420–700 nm range were extracted from hyperspectral fluorescence images obtained using ultraviolet excitation. The fluorescence-based discrimination accuracies were 100% and 99.0% for viable and non-viable cucumber seeds, respectively. The results demonstrate that hyperspectral fluorescence imaging technique has potential for quality sorting of cucumber seeds based on viability. This study benefits produce growers, as well as produce industries and researchers working to develop rapid assessment techniques for seed germination quality.

Technical Abstract: In this study, we developed a nondestructive method for discriminating viable cucumber (Cucumis sativus) seeds based on hyperspectral fluorescence imaging. The fluorescence spectra of cucumber seeds in the 420–700 nm range were extracted from hyperspectral fluorescence images obtained using 365 nm ultraviolet excitation. Four kinds of algorithms, using single-waveband images or multi-waveband images, were developed to discriminate viable and nonviable seeds. The optimal wavebands for each algorithm to use were determined using correlation analysis. The single waveband image (SWI) algorithm based on 684 nm image yielded discrimination accuracies of 99.0% and 97.0% for viable seeds and nonviable seeds, respectively. The discrimination accuracies of the algorithms based on the subtraction image (S621-425), the ratio image (R602/530), and the ratio-subtraction image (R520-698/602-698) were 100% and 99.0% for viable and non-viable seeds, respectively. The results demonstrate that hyperspectral fluorescence imaging technique has potential for quality sorting of cucumber seeds based on viability.