Browse > Article
http://dx.doi.org/10.5307/JBE.2012.37.6.411

Nondestructive Classification of Viable and Non-viable Radish (Raphanus sativus L) Seeds using Hyperspectral Reflectance Imaging  

Ahn, Chi Kook (Department of Biosystems Machinery Engineering, Chungnam National University)
Mo, Chang Yeun (National Academy of Agricultural Science, Rural Development Administration)
Kang, Jum-Soon (Department of Horticultural Bioscence, Pusan National University)
Cho, Byoung-Kwan (Department of Biosystems Machinery Engineering, Chungnam National University)
Publication Information
Journal of Biosystems Engineering / v.37, no.6, 2012 , pp. 411-419 More about this Journal
Abstract
Purpose: Nondestructive evaluation of seed viability is a highly demanded technique in the seed industry. In this study, hyperspectral imaging system was used for discrimination of viable and non-viable radish seeds. Method: The spectral data with the range from 400 to 1000 nm measured by hyperspectral reflectance imaging system were used. A calibration and a test models were developed by partial least square discrimination analysis (PLS-DA) for classification of viable and non-viable radish seeds. Either each data set of visible (400~750 nm) and NIR (750~1000 nm) spectra and the spectra of the combined spectral ranges were used for developing models. Results: The discrimination accuracy of calibration was 84% for visible range and 76.3% for NIR range. The discrimination accuracy of test was 84.2% for visible range and 75.8% for NIR range. The discrimination accuracies of calibration and test with full range were 92.2% and 92.5%, respectively. The resultant images based on the optimal PLS-DA model showed high performance for the discrimination of the nonviable seeds from the viable seeds with the accuracy of 95%. Conclusions: The results showed that hyperspectral reflectance imaging has good potential for discriminating nonviable radish seeds from massive amounts of viable seeds.
Keywords
Radish seed; Seed viability; Nondestructive sorting; Hyperspectral image; Image processing;
Citations & Related Records
Times Cited By KSCI : 4  (Citation Analysis)
연도 인용수 순위
1 Henk, J., S. Rob Van der, F. Angela, G. Jaap, P. Van and J. B. Raoul. 1998. Chlorophyll fluorescence of brassica oleracea seeds as a non-destructive marker for seed maturity and seed performance. Journal of Seed Science Research 8:437-443.
2 Kang, J. S., B. G. Son, Y. W. Choi, Y. J. Lee, W. H. Joo, C. S. Lim and Y. H. Park. 2009. Effects of dehydration methods and storage conditions on germinability of pelleted carrot seeds. Journal of Life Science 19(4):526-531. (In Korean, with English abstract)   DOI
3 Kang, J. S. and I. S. Choi. 2006. Leakage of seed reserve nutrient in artificially aged pepper seeds and enhancement of seed vigor by priming. Journal of Life Science 16(2):352-356. (In Korean, with English abstract)   DOI
4 Kang, W. S. 2008. Nondestructive determination of seed viability by optical methods. PhD diss. Daegu University, Department of Natural Resources.
5 Kim, M. S., Y. R. Chen and P. M. Mehl, 2001, Hyperspectral reflectance and fluorescence imaging system for food quality and safety. Transactions of the ASAE 44(3): 721-729.
6 Lim, J. G., S. W. Kang, K. J. Lee, C. Y. Mo and J. Y. Son. 2011. Identification of foreign objects in soybeans using near-infrared spectroscopy. Journal of Food Engineering Progress 15(2):136-142. (In Korean, with English abstract)
7 Min, T. G. and W. S. Kang. 2003. Nondestructive separation of viable and non-viable gourd (Lagenaria siceraria) seeds using single seed near infrared reflectance spectroscopy. Journal of Korean Horticultural Science and Technology 44(5):545-548.
8 Min, T. G. and W. S. Kang. 2008(a). Nondestructive classification of viable and nonviable radish (Raphanus sativus L.) seeds using single near infrared spectroscopy. Journal of Horticulture environment and biotechnology 49(1):42-46.
9 Ahn, C. K., B. K. Cho, J. S. Kang and K. J. Lee. 2012. Study on non-destructive sorting technique for lettuce (Lactuca sativa L) seed using Fourier transform near-infrared spectrometer. CNU Journal of Agricultural Science 39(1):111-116. (In Korean, with English abstract)   과학기술학회마을   DOI
10 Anatoly, A. G., C. Buschmann and H. K. Lichtenthaler. 1999. The chlorophyll fluorescence ratio F735/F700 as an accurate measure of the chlorophyll content in plants. Journal of Remote Sensing Environment 69(3): 296-302.   DOI
11 Cho, B. K., Y. R. Chen and M. S. Kim. 2007. Multispectral detection of organic residues on poultry processing plant equipment based on hyperspectral reflectance imaging technique. Computers and Electronics in Agriculture 57:177-189.   DOI
12 Chung, H. I. and H. J. Kim. 2000. Near-infrared spectroscopy: principles. Journal of Korean Analytical Science & Technology 13(1):1A-14A. (In Korean)
13 Ernst, L., J. Mocak, K. Serdt, B. Balla, T. Wenzl, D. Bandoniene, M. Gfrerer and S. Wagner. 2004. Chemometrical classification of pumpkin seed oils using UV-Vis, NIR and FTIR spectra. Journal of Biochemical and Biophysical Methods 61(1-2):95-106.   DOI
14 Fassio, A. and D. Cozzolino. 2004. non-destructive prediction of chemical composition in sunflower seeds by near infrared spectroscopy. Journal of Industrial Crops and Products 20(3):321-329.   DOI   ScienceOn
15 Shetty, N., T. G. Min, M. H. Olesen and B. Boelt. 2011. Optimal sample size for predicting viability of cabbage and radish seeds based on near infrared spectra of single seeds. Journal of Near Infrared spectroscopy 19(6):451-461.   DOI
16 Min, T. G. and W. S. Kang. 2008(b). Nondestructive classification between normal and artificially aged corn (Zea mays L.) seeds using near infrared spectroscopy. Korean journal of Crop Science 53(3):314-319.   과학기술학회마을