DOI QR코드

DOI QR Code

Development of Non-Destructive Sorting Technique for Viability of Watermelon Seed by Using Hyperspectral Image Processing

초분광 영상기술을 이용한 수박종자 발아여부 비파괴 선별기술 개발

  • 배형진 (충남대학교 바이오시스템기계공학과) ;
  • 서영욱 (충남대학교 바이오시스템기계공학과) ;
  • 김대용 (CJ대한통운 연구소) ;
  • ;
  • 박은수 (충남대학교 바이오시스템기계공학과) ;
  • 조병관 (충남대학교 바이오시스템기계공학과)
  • Received : 2015.11.26
  • Accepted : 2016.01.20
  • Published : 2016.02.28

Abstract

Seed viability is one of the most important parameters that is directly related with seed germination performance and seedling emergence. In this study, a hyperspectral imaging (HSI) system having a range of 1000-2500 nm was used to classify viable watermelon seeds from nonviable seeds. In order to obtain nonviable watermelon seeds, a total of 96 seeds were artificially aged by immersing the seeds in hot water ($25^{\circ}C$) for 15 days. Further, hyperspectral images for 192 seeds (96 normal and 96 aged) were acquired using the developed HSI system. A germination test was performed for all the 192 seeds in order to confirm their viability. Spectral data from the hyperspectral images of the seeds were extracted by selecting pixels from the region of interest. Each seed spectrum was averaged and preprocessed to develop a classification model of partial least square discriminant analysis (PLS-DA). The developed PLS-DA model showed a classification accuracy of 94.7% for the calibration set, and 84.2% for the validation set. The results demonstrate that the proposed technique can classify viable and nonviable watermelon seeds with a reasonable accuracy, and can be further converted into an online sorting system for rapid and nondestructive classification of watermelon seeds with regard to viability.

본 연구에서는 발아여부를 고속 대량으로 측정 가능한 초분광 영상 시스템 기반의 비파괴 선별기술을 개발하고자 하였다. 수박의 건전종자 96립과 퇴화종자 96립을 초분광 단파적외선 시스템을 이용하여 측정하였으며, 종자발아검증은 국제종자검정협회(ISTA)규정에 맞추어 5~14일 동안 $25^{\circ}C$에서 BP(between paper)법을 이용하여 실시하였다. 스펙트럼 데이터는 초분광 영상 시스템을 이용하여 데이터를 획득하였으며, 종자 판별모델 개발에는 PLS-DA(partial least square - discriminant analysis)를 적용하였다. PLS-DA분석법을 이용한 종자의 발아여부 판별 결과는 mean normalization을 이용하여 데이터 전처리를 이용할 경우가 가장 우수했으며, calibration의 경우 94.7%의 분류 정확도를 보였으며, validation의 경우 84.2%의 분류 정확도를 나타내어 평균적으로 90.8%의 정확도를 보였다. 이러한 결과는 종자가 퇴화하면서 야기되는 구성성분물질의 차이로 인한 것으로 사료되며, 두 그룹의 분류에 주요한 영향을 끼친 요인의 파악 및 적용을 통해 종자선별기의 개발이 가능함을 보였다.

Keywords

References

  1. M. S. Kim, Y. R. Chen, B. K. Cho, K. Chao, C.-C. Yang, A. M. Lefcourt and D. Chan, "Hyperspectral reflectance and fluorescence line-scan imaging for online defect and fecal contamination inspection of apples," Sensing and Instrumentation for Food Quality and Safety, Vol. 1, No. 3, pp. 151-159 (2007) https://doi.org/10.1007/s11694-007-9017-x
  2. W. S. Shin, "Current status of global seed industry and role of golden seed project in Korea", Journal of Plant Biotechnology, Vol. 42, No. 2, pp. 71-76 (2015) https://doi.org/10.5010/JPB.2015.42.2.71
  3. R. P. Moore, "Life alone is not enough-How alive are seeds?" Seedmen's Digest, USA, pp. 12-13 (1955)
  4. H. Hill, A. Taylor and T. Min, "Density separation of imbibed and primed vegetable seeds," Journal of the American Society for Horticultural Science, Vol. 114, No. 4, pp. 661-665 (1989)
  5. J. G. Hampton and D. M. TeKRONY, "Handbook of Vigour Test Methods," Handbook of Vigour Test Methods, Ed. 3, USA, pp. 72 (1995)
  6. M. Santos, A. Novembre and J. Marcos-Filho, "Tetrazolium test to assess viability and vigour of tomato seeds," Seed Science and Technology, Vol. 35, No. 1, pp. 213-223 (2007) https://doi.org/10.15258/sst.2007.35.1.19
  7. A. Mansouri, A. H. Mirzabe and A. Raufi, "Physical properties and mathematical modeling of melon (Cucumis melo L.) seeds and kernels," Journal of the Saudi Society of Agricultural Sciences (2015)
  8. H. Cen and Y. He, "Theory and application of near infrared reflectance spectroscopy in determination of food quality," Trends in Food Science & Technology, Vol. 18, No. 2, pp. 72-83 (2007) https://doi.org/10.1016/j.tifs.2006.09.003
  9. H. Cen and Y. He, "Theory and application of near infrared reflectance spectroscopy in determination of food quality," Trends in Food Science & Technology, Vol. 18, No. 2, pp. 72-83 (2007) https://doi.org/10.1016/j.tifs.2006.09.003
  10. R. Chalucova, G. Krivoshiev, M. Mukarev, V. Kalinov and C. Scotter, "Determination of green pea maturity by measurement of whole pea transmittance in the NIR region," LWT-Food Science and Technology, Vol. 33, No. 7, pp. 489-498 (2000) https://doi.org/10.1006/fstl.2000.0704
  11. T. H. Kim, S. Y. Chung, N. Park, S.-Y. Hamm, S. Y. Lee and B.-W. Kim, "Combined analyses of chemometrics and kriging for identifying groundwater contamination sources and origins at the Masan coastal area in Korea," Environmental Earth Sciences, Vol. 67, No. 5, pp. 1373-1388 (2012) https://doi.org/10.1007/s12665-012-1582-6
  12. D. Wu, L. Feng, Y. He and Y. Bao, "Variety identification of Chinese cabbage seeds using visible and near-infrared spectroscopy," Transactions of the ASABE, Vol. 51, No. 6, pp. 2193-2199 (2008) https://doi.org/10.13031/2013.25382
  13. N. Shetty, T.-G. Min, R. Gislum, M. Olesen and B. Boelt, "Optimal sample size for predicting viability of cabbage and radish seeds based on near infrared spectra of single seeds," Journal of Near Infrared Spectroscopy, Vol. 19, No. 6, pp. 451 (2012) https://doi.org/10.1255/jnirs.966
  14. S. Lohumi, C. Mo, J.-S. Kang, S.-J. Hong and B.-K. Cho, "Nondestructive evaluation for the viability of watermelon (citrullus lanatus) seeds using fourier transform near infrared spectroscopy," Journal of Biosystems Engineering, Vol. 38, No. 4, pp. 312-317 (2013) https://doi.org/10.5307/JBE.2013.38.4.312
  15. A. Ambrose, S. Lohumi, W.-H. Lee and B. K. Cho, "Comparative nondestructive measurement of corn seed viability using Fourier transform near-infrared (FT-NIR) and Raman spectroscopy," Sensors and Actuators B: Chemical, Vol. 224, pp. 500-506 (2015)
  16. C.-K. Ahn, B.-K. Cho, C. Y. Mo and M. S. Kim, "Study on development of non-destructive measurement technique for viability of lettuce seed (Lactuca sativa L) using hyperspectral reflectance imaging," Journal of the Korean Society for Nondestructive Testing, Vol. 32, No. 5, pp. 518-525 (2012) https://doi.org/10.7779/JKSNT.2012.32.5.518
  17. C. Mo, G. Kim, K. Lee, M. S. Kim, B.-K. Cho, J. Lim and S. Kang, "Non-destructive quality evaluation of pepper (Capsicum annuum L.) seeds using LED-induced hyperspectral reflectance imaging," Sensors, Vol. 14, No. 4, pp. 7489-7504 (2014) https://doi.org/10.3390/s140407489
  18. H. S. Kwak, M. Kim, Y. Lee and Y. Jeong, "Identification of key sensory attributes for consumer acceptance and instrumental quality of aseptic-packaged cooked rice," International Journal of Food Science & Technology, Vol. 50, No. 3, pp. 691-699 (2015) https://doi.org/10.1111/ijfs.12684
  19. J. S. Shenk, J. J. Workman and M. O. Westerhaus, "Application of NIR spectroscopy to agricultural products, in Handbook of Near-Infrared Analysis," D.A. Burns and E.W. Ciurczak, Editors. Marcel Dekker: New York, USA (2001)
  20. E. C. Keeffe, "Rapid nutrient determination of sugarcane milling by-products using near infrared spectroscopy," Queensland University of Technology (2013)
  21. I. Murray. and P. C. Williams, "Chemical principles of near-infrared technology, in Nearinfrared technology in the agricultural and food indusries," P. Williams and K. Norris, Editors, American Association of Cereal Chemists: St. Paul, Minnesota, USA (1987)
  22. G. R. Hunt., "Spectral signatures of particulate minerals in the visible and near infrared," Geophysics, Vol. 42, No. 3, pp. 501-513 (1977) https://doi.org/10.1190/1.1440721

Cited by

  1. Assessment of seed quality using non-destructive measurement techniques: a review vol.26, pp.04, 2016, https://doi.org/10.1017/S0960258516000234
  2. Single-Kernel FT-NIR Spectroscopy for Detecting Supersweet Corn (Zea mays L. Saccharata Sturt) Seed Viability with Multivariate Data Analysis vol.18, pp.4, 2018, https://doi.org/10.3390/s18041010