Food Engineering Progress (산업식품공학)

Korean Society for Industrial Food Engineering (한국산업식품공학회)
권호 표지

Prediction of Internal Quality for Cherry Tomato using Hyperspectral Reflectance Imagery

초분광 반사광 영상을 이용한 방울토마토 내부품질 인자 예측

  • Kim, Dae-Yong (Department of Biosystems Machinery Engineering, Chungnam National University) ;
  • Cho, Byoung-Kwan (Department of Biosystems Machinery Engineering, Chungnam National University) ;
  • Kim, Young-Sik (Department of Plant Industry Engineering, Sangmyung University)
  • 김대용 (충남대학교 바이오시스템기계공학과) ;
  • 조병관 (충남대학교 바이오시스템기계공학과) ;
  • 김영식 (상명대학교 식물산업공학과)
  • Received : 2011.07.22
  • Accepted : 2011.10.26
  • Published : 2011.11.30
⟨ Previous Next ⟩

Abstract

Hyperspectral reflectance imaging technology was used to predict internal quality of cherry tomatoes with the spectral range of 400-1000 nm. Partial least square (PLS) regression method was used to predict firmness, sugar content, and acid content. The PLS models were developed with several preprocessing methods, such as normalization, standard normal variate (SNV), multiplicative scatter correction (MSC), and derivative of Savitzky Golay. The performance of the prediction models were investigated to find the best combination of the preprocessing and PLS models. The coefficients of determination ($R^{2}_{p}$) and standard errors of prediction (SEP) for the prediction of firmness, sugar content, and acid content of cherry tomatoes from green to red ripening stages were 0.876 and 1.875kgf with mean of normalization, 0.823 and $0.388^{\circ}Bx$ with maximum of normalization, and 0.620 and 0.208% with maximum of normalization, respectively.

초분광영상을 이용하여 방울토마토의 전체 면에서 반사스펙트럼을 획득하였으며 숙도 등급(GN-RD)에 따른 스펙트럼의 차이를 관찰하였다. 방울토마토의 반사스펙트럼에서 클로로필에 의한 675 nm 영역의 흡수가 관찰되었고, 당과 수분의 영향으로 알려진 840 nm, 970 nm 영역에서 흡수가 관찰되었다. 특히 GN에서 RD 등급으로 숙도가 진행될수록 평균 스펙트럼의 경우 반사율이 낮아지는 경향이 관찰되었다. 총 8개의 전처리를 이용하여 전 숙도 등급의 시료에 적용한 PLS 회귀 분석에서 내부품질들 중 경도 예측모델이 가장 우수한 것으로 확인되었다. 이때 전처리는 평균값을 이용한 정규화이었으며 결정계수는 0.876, 그리고 SEP은 1.875kgf이었다. 당도의 경우는 최대값을 이용한 정규화에서 결정계수가 0.823과 SEP $0.388^{\circ}Bx$로 나타났으며, 산함량의 경우 최대값을 이용한 정규화에서 0.620의 결정계수와 0.208%의 SEP이 확인되었다. 상품성을 고려한 PK, LR, RD 등급의 시료에서 PLS 회귀 분석을 실시한 결과 내부품질 중 전체의 숙도 등급의 시료를 사용하여 예측한 결과보다는 전체적으로 다소 낮은 예측결과를 확인할 수 있었다. 내부 품질 중 경도에서 가장 높은 예측모델이 확인되었으며, 전처리는 일정 범위를 이용한 정규화이고 0.679의 결정계수와 $0.976^{\circ}Bx$의 SEP이 확인되었다. 당도는 최대값을 이용한 정규화에서 0.586의 결정계수와 0.546kgf의 SEP의 결과를 보였으며 산 함량은 Savitzky Golay의 2차 미분에서 0.547의 결정계수와 0.188%의 SEP을 보였다. 본 연구에서는 최근 연구 활용이 시작되고 있는 최신기술인 초분광 반사영상을 이용하여 방울토마토 내부품질인 경도, 당도, 산 함량 예측의 가능성을 확인하였다. 초분광 영상은 영상처리를 이용하여 외부의 결함 및 외부 착색도등도 측정할 수 있으므로 본 연구에서 수행한 내부품질 측정과 융합하여 복합적인 농산물 품질 선별기 개발에 활용할 수 있을 것으로 판단된다.

Keywords

Acknowledgement

Supported by : 농림수산식품부

References

  1. Chae JC. 2004. Quality Evaluation and Control of Agricultural Products. Hayngmoonsa, Seoul, Korea, pp. 13-17.
  2. Cho HS. 2000. Measurement of apple firmness by VIS/NIR transmittance. MS thesis. Seoul National University, Seoul, Korea.
  3. Cho BK, Chen YR, Kim MS. 2007. Multispectral detection of organic residues on poultry processing plant equipment based on hyperspectral reflectance imaging technique. Comput. Electron Agr. 57: 177-189. https://doi.org/10.1016/j.compag.2007.03.008
  4. ElMasry G, Wang N, Elsayed A, Ngadi M. 2007. Hyperspectral imaging for nondestructive determination of some quality attributes for strawberry. J. Food Eng. 81: 98-107. https://doi.org/10.1016/j.jfoodeng.2006.10.016
  5. ElMasry G, Wang N, Vigneault C, Qiao J, ElSayed A. 2008. Early detection of apple bruises on different background colors using hyperspectral imaging. LWT-Food Sci. Technol. 41: 337-345. https://doi.org/10.1016/j.lwt.2007.02.022
  6. Kim MS, Chen Y, Mehl PM. 2001. Hyperspectral reflectance and fluorescence imaging system for food safety and quality. Trans. ASABE. 44: 721-729.
  7. Kim DY, Cho BK, Mo CY, Kim YS. 2010. Study on prediction of internal quality of cherry tomato using Vis/NIR spectroscopy. J. Biosystems Eng. 35: 450-457. https://doi.org/10.5307/JBE.2010.35.6.450
  8. Kim DY, Lee NG, Back IS, Cho BK. 2010. Study on detection of damage on apple 'Fuji' using multispectral imagery. In: Proceedings of the KSAM Winter Conference. February 19, Jeonju, Korea, pp. 19-22.
  9. Lee KJ, Kang SW, Choi KH. 2004. Nondestructive quality measurement of fruits and vegetables using near-infrared spectroscopy. Food Eng. Prog. 8: 158-169.
  10. Lee NG, Cho BK, Kim MS. 2009. Study on bruise detecting at the inner parts of pears using hyperspectral imaging. In: Proceedings of the KSAM Summer Conference. July 9, Sokcho, Korea, pp. 434-437.
  11. Lee NG. 2010. Study on bruise detecting technique using hyperspectral imaging system. MS thesis. Chungnam National University, Daejeon, Koera.
  12. Lu R, Peng Y. 2006. Hyperspectral scattering for assessing peach fruit firmness. Biosyst. Eng. 93: 161-171. https://doi.org/10.1016/j.biosystemseng.2005.11.004
  13. Noh HK, Lu R. 2009. Apple quality measurement using hyperspectral reflectance and fluorescence scattering. J. Biosystems Eng. 34: 37-43. https://doi.org/10.5307/JBE.2009.34.1.037
  14. Noh HK, Lu R. 2010. UV/blue light-induced fluorescence assessing apple quality. J. Biosystems Eng. 35: 124-131. https://doi.org/10.5307/JBE.2010.35.2.124
  15. Park WP, Cho SH, Kim CH. 2004. Quality characteristics of cherry tomatoes packaged with paper bag incorporated with antimicrobial agents. J. Korean Soc. Food Sci. Nutr. 33: 1381- 1384. https://doi.org/10.3746/jkfn.2004.33.8.1381
  16. Polder G, Heijden GWAM, Voet H, Young IT. 2004. Measuring surface distribution of carotenes and chlorophyll in ripening tomatoes using imaging spectrometry. Postharvest Biol. Technol. 34: 117-129. https://doi.org/10.1016/j.postharvbio.2004.05.002
  17. Peng Y, Lu R. 2008. Analysis of spatially resolved hyperspectral scattering images for assessing apple fruit firmness and soluble solids content. Postharvest Biol. Technol. 48: 52-62. https://doi.org/10.1016/j.postharvbio.2007.09.019
  18. Qin J, Burks TF, Kim MS, Chao K, Ritenour MA. 2008. Citrus canker detection using hyperspectral reflectance imaging and PCA-based image classification method. Sens. Instrumen. Food Qual. 2: 168-177. https://doi.org/10.1007/s11694-008-9043-3
  19. Ryu DS, Hwang IG, Noh SH. 2000. Pre-processing techniques on VIS/NIR spectral data for non-destructive quality evaluation of fruits. In: Proceedings of the Korean Society Agricultural Machinery 2000 Winter Conference. February 18, Suwon, Korea, pp. 451-456.
  20. Suh SR, Lee KH, Yu SH, Yoo SN, Choi YS. 2011. Comparison of performance of measuring method of VIS/NIR spectroscopic spectrum to predict soluble solids content of 'Shingo' pear. J. Biosystems Eng. 36: 130-139. https://doi.org/10.5307/JBE.2011.36.2.130
  21. USDA. 1997. United States Standards for Grades of Fresh Tomatoes. United States Department of Agriculture, Agricultural Marketing Service, Washington DC, USA.
  22. Xie L, Ying Y, Ying T, Yu H, Fu X. 2007. Discrimination of transgenic tomatoes based on visible/near-infrared spectra. Anal. Chim. Acta 584: 379-384. https://doi.org/10.1016/j.aca.2006.11.071
  23. Zude M, Herold B, Roger JM, Maurel VB, Landahl S. 2006. Non-destructive tests on the prediction of apple fruit flesh firmness and soluble solids content on tree and in shelf life. J. Food Eng. 77: 254-260. https://doi.org/10.1016/j.jfoodeng.2005.06.027