Journal of the Korea Academia-Industrial cooperation Society (한국산학기술학회논문지)

The Korea Academia-Industrial cooperation Society (한국산학기술학회)
권호 표지
DOI QR코드

DOI QR Code

Tomato sorting using independent component analysis on RGB images

독립성분분석을 이용한 RGB 이미지 토마토 분류

  • Ban, Jong-Oh (Dept. of Internet Business, Hallym Polytechnic University) ;
  • Kwon, Ki-Hyeon (Dept. of Information & Communication Engineering, Kangwon National University)
  • 반종오 (한림성심대학교 인터넷비즈니스과) ;
  • 권기현 (강원대학교 전자정보통신공학부)
  • Received : 2012.01.03
  • Accepted : 2012.03.08
  • Published : 2012.03.31
Download PDF
⟨ Previous Next ⟩

Abstract

Tomatoes were harvested at different ripening stages. To determine the ripening stages, We analyzed the relation between the compound concentrations of tomato measured with HPLC and the tomato RGB images. Among the compound concentrations, tomato quality is mostly affected by the Lycopene. The $Q^2$ error of the predicted Lycopene concentration and the corresponding independent component of tomato RGB image, determined from the PLS procedure, was 0.92. and we show the effectiveness of the independent component by comparing the error between the pixel area of RGB image applied by independent component and the simple black white tomato image. This regression made it possible to construct concentration images of the tomatoes, which showed non-uniform ripening. The method can be applied in an unsupervised real time sorting machine of unripe and discolored tomato using the compound concentrations.

토마토는 여러 가지 다른 숙성 단계에서 수확될 수 있다. 토마토의 숙성 상태를 판단하기 위해 토마토 과육을 HPLC로 분석한 여러 가지 화합물과 토마토 RGB 이미지를 ICA로 분석한 독립성분간의 관계를 분석하였다. 여러 토마토 화합물중 품질에 가장 영향을 많이 미치는 라이코펜과 토마토 RGB 이미지의 독립성분간의 부분최소제곱 $Q^2$ 값이 0.92로 매우 높음을 알 수 있었다. 그리고 라이코펜에 대응되는 독립성분을 토마토 RGB 이미지에 적용하여 픽셀 면적을 구한 것과 단순이진 이미지로 구해진 이미지의 픽셀 면적간의 비교를 제시하여 독립성분의 유효성을 제시하였다. 독립성분을 반영한 토마토 이미지를 통해 토마토의 숙성 상태를 보여주는 것이 가능하며, ICA 독립성분을 이용한 농축이미지 생성을 통해 토마토의 색상이 좋지 않거나 라이코펜과 같은 주요 성분이 없게 된 토마토를 분류해 내는 것이 가능해진다.

Keywords

References

  1. K. Iwai, T. Suzuki, H. Fujiwake and S. Oka, "Simultaneous microdetermination of capsaicin and its four analogues by using high-performance liquid chromatography and gas chromatography-mass spectrometry," Journal of chromatography, v.172 no.1, pp.303-311, April 1979. https://doi.org/10.1016/S0021-9673(00)90966-X
  2. A. Muller-Stock, RK. Joshi and J. Buchi, "Study of the components of capsaicin. Quantitative gas chromatographic determination of individual homologs and analogs of capsaicin in mixtures from a natural source and of vanillyl pelargonic amide as adulteration," Journal of chromatography v.63, pp.281-287, 1971. https://doi.org/10.1016/S0021-9673(01)85640-5
  3. G. Polder, "Tomato sorting using independent component analysis on spectral images", Real-time imaging v.9 no.4 , pp.253-259, August 2003. https://doi.org/10.1016/j.rti.2003.09.008
  4. G. Polder, van der Heijden GWAM, van der Voet H, Young IT. "Measuring surface distribution of compounds in tomatoes using imaging spectrometry", Postharvest biology and technology v.34 no.2, pp.117-129 , Nov. 2004. https://doi.org/10.1016/j.postharvbio.2004.05.002
  5. A. Hyvarinen, E. Oja, "Independent component analysis: algorithms and applications", Neural Networks v.13, pp.411-30, 2000. https://doi.org/10.1016/S0893-6080(00)00026-5
  6. HW. Ahn, "Studies on component analysis related to quality of Korean red pepper", MS Thesis. Kyung-Hee University, 1997
  7. P. Comon, "Independent component analysis, a new concept", Signal Processing v.36, pp.287-314, April 1994. https://doi.org/10.1016/0165-1684(94)90029-9
  8. A. Hyvarinen, "Fast and robust fixed-point algorithms for independent component analysis", IEEE transactions on neural networks v.10 no.3, pp.626-634 , 1999. https://doi.org/10.1109/72.761722
  9. G. Polder, GWAM Heijden, IT. Young, "Spectral image analysis for measuring ripeness of tomatoes", Transactions of the ASAE v.45 no.4, pp.1155-1162, 2002.