대한전자공학회논문지SP (Journal of the Institute of Electronics Engineers of Korea SP)

대한전자공학회 (The Institute of Electronics and Information Engineers)
권호 표지

벼 병충해분할을 위한 색채공간의 비교연구

A Comparative Study of Different Color Space for Paddy Disease Segmentation

  • Zahangir, Alom Md. (Dept. of Electric, Electronic and Computer Engineering) ;
  • Lee, Hyo-Jong (Div. of Computer Science and Engineering, Chonbuk National University, CAIIT)
  • 투고 : 2010.12.27
  • 심사 : 2011.03.02
  • 발행 : 2011.05.25
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

전 세계적으로 벼 병충해의 인식과 분류는 농업현장에서 기술적 경제적으로 중요한 요소이다. 컴퓨터 비젼 기술은 벼 병충해를 진단하고 곡물의 효율적인 관리에 유용하다. 영역 분할은 벼 병충해를 조기에 정확하게 탐지하는데 매우 중요한 기술이다. 가우시안 평균기법을 이용한 새로운 벼 병충해 분할 방식을 다양한 색체공간에서 제안하였다. 사용 색체공간에 따라 벼 병충해의 분할에 따른 성능은 달라질 것이다. 따라서, 이 수치연구는 어느 색체공간이 벼 병충해를 분할하는데 최적한지를 결정할 목적으로 수행되었다. 본 연구는 NTSC, CIE, YCbCr, HSV, 그리고 정규화 RGB의 5개의 색체공간을 다루었다. 연구 결과는 YCbCr 색체공간이 98%의 정확도로 벼 병충해 영역을 최적으로 분할하는 것을 보여주었다. 또한 제안하는 방법은 벼 병충해의 영역을 자동화에 의하여 강건하게 분할할 수 있다는 것을 증명하였다.

The recognition and classification of paddy rice disease are of major importance to the technical and economical aspect of agricultural industry over the world. Computer vision techniques are used to diagnose rice diseases and to efficiently manage crops. Segmentation of lesions is the most important technique to detect paddy rice disease early and accurately. A new Gaussian Mean (GM) method was proposed to segment paddy rice diseases in various color spaces. Different color spaces produced different results in segmenting paddy diseases. Thus, this empirical study was conducted with the motivation to determine which color space is best for segmentation of rice disease. It included five color spaces; NTSC, CIE, YCbCr, HSV and the normalized RGB(NRGB). The results showed that YCbCr was the best color space for optimal segmentation of the disease lesions with 98.0% of accuracy. Furthermore, the proposed method demonstrated that diseases lesions of paddy rice can be segmented automatically and robustly.

키워드

참고문헌

  1. M.L.Gullino, and J.P. Stack, Crop Biosecurity Netherlands: pp. 25-36,Springer 2008.
  2. Nawala, and Moratuwa, "An Image Recognition System for Crop Disease Identification of Paddy fields in Sri Lanka," Fourth International Conference on Industrial and Information Systems, ICIIS 2009, Sri Lanka, 28-31 Dec. 2009.
  3. Qing Yao, and Baojun Yang,"Application of support vector machine for detecting paddy disease using shape and color texture features," International Conference on Engineering Computation 2009. ICEC 2009.
  4. Yingfeng Zhou, and Qing Yao, "Segmentation of Paddy Disease Spots Based on Improved BPNN," IASP10, pp.575-578, 2010.
  5. Libo Liu, and Guomin Zhou,"Extraction of the Rice Leaf Disease Image Based on BP Neural Networks," International conference on. Issue ,pp. 1 - 3, China, 11-13 Dec. 2009.
  6. Santanu Phadikar and Jaya Sil, "Rice Disease Identification using Pattern Recognition Techniques,"Proceedings of 11 International Conference on Computer and Information Technology (ICCIT 2008),Khulna, Bangladesh., 25-27 Dec, 2008.
  7. D.Moshou, and H. Ramon, "Automatic detection of 'yellow rust' in wheat using reflectance measurements and neural networks," Comput. Electron. Agric., vol 44, no.3,pp.173-188, Sept. 2004. https://doi.org/10.1016/j.compag.2004.04.003
  8. P.M. Granitto, and H.A. Ceccatto, "Large-scale investigation of weed seed identification by machine vision," Comput. Etectron. Agric., vol. 47no.1, pp.15-24, Apr.2005. https://doi.org/10.1016/j.compag.2004.10.003
  9. R. Pydipati, and W.S. Lee,"Identification of citrus disease using color texture features and discriminant analysis," Comput. Electron. Agric, vol52,no.1, pp.49-59,June 2006. https://doi.org/10.1016/j.compag.2006.01.004
  10. N. Otsu, "A threshold selection method from gray-level histogram," IEEE Trans. CSAE, vol.23, no. 6, pp. 62-66, Jan. 1979.
  11. R.M. Haralick, and I. Dinstein, "Texture features for image classification," IEEE Trans. Syst. Man Bybern., vol.3, no.6,pp.610-621, Nov. 1973.
  12. K.Y. Huang, "Application of artificial neural network for detecting phalaenopsis seedling disease using color and texture features," Comput. Electron. Agric., vol.57, no.1, pp.3-11, May 2007. https://doi.org/10.1016/j.compag.2007.01.015
  13. EI-Shshtawy T.,A. and El-Az. E, "From Deperdence Networks to KADS: Implementation Issue," in Proceedings of the 2nd Workshop on AI in Agriculture, Netherlands, 1995.
  14. Kamel A., and Sticklen J. "An Integrated Wheat Crop Management System Based on Generic Task Knowledge Based Systems and CERES Numerical Simulation," AI Applications, vol. 9, no. 1, 1995.
  15. Refea M. and Rafea A.,"LIMEX: An Integrated Multimedia Expert System," In Proceedings of the International Conference on Multimedia Modeling, Singapore, 1997.
  16. Rafea A.,and Mahmoud M.,"Experience with the Development and Deployment of Expert Systems in Agriculture," in Proceeding of IAAI-95 Conference, Montreal-Canada, 1995.
  17. Salah A., and Farahat H., "CITEX: An Expert System for Citrus Crop Management," in Proceedings of ESADW 93, MOALR, Cairo, Egypt,1993.
  18. Pankaj Kumar, and Surendra Ranganath "A Comparative Study of Different Color space for Foreground and Shadow Detection for Traffic Monitoring System," IEEE 5th International Conference on Intelligent Transportation System, Singapore, September 2002.
  19. A. Camargo and J.S. Smith, "An image-processing based algorithm to automatically identify plant disease visual symptoms," Biosystems Engineering, vol.102, pp.9-21, 2009. https://doi.org/10.1016/j.biosystemseng.2008.09.030
  20. Gonzales and R. E. Woods."Digital Image Processing," Prentice Hall, 2002.
  21. K.V. Mardia, "Statistics of directional data.," Academic Press, London, 1972.
  22. B.C. Lovell, and R.C Williamson. "The circular nature of discrete-time frequency estimates," In IEEE International Conference on ASSP, pp. 3369-3372, Toronto, May 1991.
  23. J. N. Kapur, and A.K.C. Wong,"A new method for gray-level picture threshodling using the entropy of the histogram," Computer Vision Graphics Image Process. Vol 29, pp.273-285, 1985. https://doi.org/10.1016/0734-189X(85)90125-2