Machine Vision and Applications

, Volume 27, Issue 5, pp 625–635 | Cite as

On the value of the Kullback–Leibler divergence for cost-effective spectral imaging of plants by optimal selection of wavebands

  • Landry Benoit
  • Romain Benoit
  • Étienne Belin
  • Rodolphe Vadaine
  • Didier Demilly
  • François Chapeau-Blondeau
  • David RousseauEmail author
Special Issue Paper


The practical value of a criterion based on statistical information theory is demonstrated for the selection of optimal wavelength and bandwidth of low-cost lighting systems in plant imaging applications. Kullback–Leibler divergence is applied to the problem of spectral band reduction from hyperspectral imaging. The results are illustrated on various plant imaging problems and show similar results to the one obtained with state-of-the-art criteria. A specific interest of the proposed approach is to offer the possibility to integrate technological constraints in the optimization of the spectral bands selected.


Spectral imaging Information theory Plant imaging 



This work received support from the French Government supervised by the Agence Nationale de la Recherche in the framework of the program Investissements d’Avenir under reference ANR-11-BTBR-0007 (AKER program). Landry BENOIT gratefully acknowledges financial support from Angers Loire Metropole and GEVES-SNES for the preparation of his PhD.


  1. 1.
    Thenkabail, P.S., Lyon, J.G.: Huete: Hyperspectral Remote Sensing of Vegetation. CRC Press, Boca Raton (2011)CrossRefGoogle Scholar
  2. 2.
    Bock, C.H., Poole, G.H., Parker, P.E., Gottwald, T.: Plant disease severity estimated visually, by digital photography and image analysis, and by hyperspectral imaging. Crit. Rev. Plant Sci. 29, 59–107 (2010)CrossRefGoogle Scholar
  3. 3.
    Grahn, H., Geladi, P.: Techniques and Applications of Hyperspectral Image Analysis. Wiley, New York (2007)CrossRefGoogle Scholar
  4. 4.
    Vigneau, N., Ecarnot, M., Rabatel, G., Roumet, P.: Potential of field hyperspectral imaging as a non destructive method to assess leaf nitrogen content in Wheat. Field Crops Res. 122, 25–31 (2011)CrossRefGoogle Scholar
  5. 5.
    Behmann, J., Mahlein, A.K., Paulus, S., Kuhlmann, H., Oerke, E. C., Plumer, L.: Generation and application of hyperspectral 3D plant models. In: Agapito, L., Bronstein, M.M., Rother, C. (eds.) Computer Vision-ECCV 2014 Workshops. 70, 117–130. Springer, New York (2014)Google Scholar
  6. 6.
    Rousseau, D., Chéné, Y., Belin, E., Semaan, G., Trigui, G., Boudehri, K., Franconi, F., Chapeau-Blondeau, F.: Multiscale imaging of plants: current approaches and challenges. Plant Methods 11, 1–6 (2015)CrossRefGoogle Scholar
  7. 7.
    Tsaftaris, S.A.: Noutsos: plant phenotyping with low cost digital cameras and image analytics. In: Athanasiadis, I.N., Rizzoli, A.E., Mitkas, P.A., Gómez, M.J. (eds.) Information Technologies in Environmental Engineering, pp. 238–251. Springer, Berlin (2009)CrossRefGoogle Scholar
  8. 8.
    Kleynen, O., Leemans, V., Destain, M.-F.: Selection of the most efficient wavelength bands for Jonagold apple sorting. Postharvest Biol. Technol. 30, 221–232 (2003)CrossRefGoogle Scholar
  9. 9.
    Piron, A., Leemans, V., Kleynen, O., Lebeau, F., Destain, M.-F.: Selection of the most efficient wavelength bands for discriminating weeds from crop. Comput. Electron. Agric. 62, 141–148 (2008)CrossRefGoogle Scholar
  10. 10.
    Feyaerts, F., Van Gool, K.: Multi-spectral vision system for weed detection. Pattern Recognit. Lett. 22, 667–674 (2001)CrossRefzbMATHGoogle Scholar
  11. 11.
    Chao, K., Chen, Y., Hruschka, W., Park, B.: Chicken heart disease characterization by multi-spectral imaging. Appl. Eng. Agric. 17, 99–106 (2001)CrossRefGoogle Scholar
  12. 12.
    Pal, M.: Margin-based feature selection for hyperspectral data. Int. J. Appl. Earth Obs. Geoinf. 11, 212–220 (2009)CrossRefGoogle Scholar
  13. 13.
    Pal, M.: Multinomial logistic regression-based feature selection for hyperspectral data. Int. J. Appl. Earth Obs. Geoinf. 14, 214–220 (2012)CrossRefGoogle Scholar
  14. 14.
    Guo, G., Gunn, S., Damper, R., Nelson, J.: Band selection for hyperspectral image classification using mutual information. IEEE Geosci. Remote Sens. Lett. 3, 522–526 (2000)CrossRefGoogle Scholar
  15. 15.
    De Backer, S., Kempeneers, P., Debruyn, W., Scheunders, P.: A band selection technique for spectral classification. IEEE Geosci. Remote Sens. Lett. 2, 319–323 (2005)CrossRefGoogle Scholar
  16. 16.
    Nakauchi, S., Nishino, K., Yamashita, T.: Selection of optimal combinations of band-pass filters for ice detection by hyperspectral imaging. Opt. Express 20, 986–1000 (2012)CrossRefGoogle Scholar
  17. 17.
    Richter, M., Beyerer, J.: Optical filter selection for automatic visual inspection. In: IEEE Winter Conference on Applications of Computer Vision (WACV) 5, 123–128 (2014)Google Scholar
  18. 18.
    Hansen, P.M., Schjoerring, J.K.: Reflectance measurement of canopy biomass and nitrogen status in wheat crops using normalized difference vegetation indices and partial least squares regression. Remote Sens. Environ. 86, 542–553 (2003)CrossRefGoogle Scholar
  19. 19.
    Thenkabail, P.S., Smith, R.B., De Pauw, E.: Evaluation of narrowband and broadband vegetation indices for determining optimal hyperspectral wavebands for agricultural crop characterization. Photogr. Eng. Remote Sens. 68, 607–622 (2002)Google Scholar
  20. 20.
    Fiorani, F., Rascher, U., Jahnke, S., Schurr, U.: Imaging plants dynamics in heterogenic environments. Curr. Opin. Biotechnol. 23, 227–235 (2012)CrossRefGoogle Scholar
  21. 21.
    Wold, S., Ruhe, A., Wold, H., Dunn, I.: The collinearity problem in linear regression. The partial least squares (PLS) approach to generalized inverses. SIAM J. Sci. Stat. Comput. 5, 735–743 (1984)CrossRefzbMATHGoogle Scholar
  22. 22.
    Osborne, S., Kunnemeyer, R., Jordan, R.: Method of wavelength selection for partial least squares. Analyst 122, 1531–1537 (1997)CrossRefGoogle Scholar
  23. 23.
    Benoit, L., Belin, E., Rousseau, D., Chapeau-Blondeau, F.: Information-theoretic modeling of trichromacy coding of light spectrum. Fluct. Noise Lett. 13, 1–23 (2014)CrossRefGoogle Scholar
  24. 24.
    Basseville, M.: Divergence measures for statistical data processing: an annotated bibliography. Signal Process. 93, 621–633 (2013)CrossRefGoogle Scholar
  25. 25.
    Bowen, J.K., Mesarich, C.H., Bus, V.G., Beresford, R.M., Plummer, K.M.: Templeton: \({Venturia\, inaequalis}\): the causal agent of apple scab. Mol. Plant Pathol. 12, 105–122 (2011)CrossRefGoogle Scholar
  26. 26.
    Oerke, E.C., Frohling, P., Steiner, U.: Thermographic assessment of scab disease on apple leaves. Precis. Agric. 12, 699–715 (2011)CrossRefGoogle Scholar
  27. 27.
    Chéné, Y., Rousseau, D., Lucidarme, P., Bertheloot, J., Caffier, V., Morel, P., Belin, E., Chapeau-Blondeau, F.: On the use of depth camera for 3D phenotyping of entire plants. Comput. Electron. Agric. 82, 122–127 (2012)CrossRefGoogle Scholar
  28. 28.
    Belin, E., Rousseau, D., Boureau, T., Caffier, V.: Thermography versus chlorophyll fluorescence imaging for detection and quantification of apple scab. Comput. Electron. Agric. 90, 159–163 (2013)CrossRefGoogle Scholar
  29. 29.
    Delalieux, S., Auwerkerken, A., Verstraeten, W.W., Somers, B., Valcke, R., Lhermitte, S., Coppin, P.: Hyperspectral reflectance and fluorescence imaging to detect scab induced stress in apple leaves. Remote Sens. 1, 858–874 (2009)CrossRefGoogle Scholar
  30. 30.
    Mahesh, S., Manickavasagan, A., Jayas, D.S., Paliwal, J., White, N.D.G.: Feasibility of near-infrared hyperspectral imaging to differentiate Canadian wheat classes. Biosyst. Eng. 101, 50–57 (2008)CrossRefGoogle Scholar
  31. 31.
    Mahesh, S., Jayas, D.S., Paliwal, J., White, N.D.G.: Identification of wheat classes at different moisture levels using near-infrared hyperspectral images of bulk samples. Sen. Instrum. Food Qual. Saf. 5, 1–9 (2011)CrossRefGoogle Scholar
  32. 32.
    Manickavasagan, A., Jayas, D.S., White, N.D.G., Paliwal, J.: Wheat class identification using thermal imaging. Food Bioprocess Technol. 3, 450–460 (2010)CrossRefGoogle Scholar
  33. 33.
    Forcella, F., Arnold, R.L.B., Sanchez, R., Ghersa, C.M.: Modeling seedling emergence. Field Crops Res. 67, 123–139 (2000)CrossRefGoogle Scholar
  34. 34.
    Belin, E., Rousseau, D., Rojas-Varela, J., Demilly, D., Wagner, M.H., Cathala, M.H., Durr, C.: Thermography as non invasive functional imaging for monitoring seedling growth. Comput. Electron. Agric. 70, 236–240 (2011)CrossRefGoogle Scholar
  35. 35.
    Benoit, L., Belin, E., Durr, C., Chapeau-Blondeau, F., Demilly, D., Ducournau, S., Rousseau, D.: Computer vision under inactinic light for hypocotyl radicle separation with a generic gravitropism-based criterion. Comput. Electron. Agric. 111, 12–17 (2015)CrossRefGoogle Scholar
  36. 36.
    Murakami, Y., Obi, T., Yamaguchi, M., Ohyama, N., Komiya, Y.: Spectral reflectance estimation from multi-band image using color chart. Opt. Commun. 188, 47–54 (2001)CrossRefGoogle Scholar
  37. 37.
    Hernández-Andrés, J., Nieves, J.I., Valero, E.M., Romero, J.: Spectral-daylight recovery by use of only a few sensors. J. Opt. Soc. Am. A 21, 13–23 (2004)CrossRefGoogle Scholar
  38. 38.
    Cheung, V., Westland, S., Li, C., Hardeberg, J., Connah, D.: Characterization of trichromatic color cameras by using a new multispectral imaging technique. J. Opt. Soc. Am. A 22, 1231–1240 (2005)CrossRefGoogle Scholar
  39. 39.
  40. 40.
    Otsu, N.: A threshold selection method from gray-level histograms. Automatica 11, 23–27 (1975)Google Scholar
  41. 41.
    Piron, A., Leemans, V., Kleynen, O., Lebeau, F., Destain, M.-F.: Selection of the most efficient wavelength bands for discriminating weeds from crop. Comput. Electron. Agric. 2, 141–148 (2008)CrossRefGoogle Scholar
  42. 42.

Copyright information

© Springer-Verlag Berlin Heidelberg 2015

Authors and Affiliations

  • Landry Benoit
    • 1
  • Romain Benoit
    • 1
  • Étienne Belin
    • 1
  • Rodolphe Vadaine
    • 2
  • Didier Demilly
    • 2
  • François Chapeau-Blondeau
    • 1
  • David Rousseau
    • 3
    Email author
  1. 1.Laboratoire Angevin de Recherche en Ingénierie des Systèmes (LARIS)Université d’AngersAngersFrance
  2. 2.GEVES, Station Nationale d’Essais de Semences (SNES)BeaucouzéFrance
  3. 3.CREATIS; CNRS UMR 5220; INSERM U1044; Université Lyon 1, INSA-LyonUniversité de LyonVilleurbanneFrance

Personalised recommendations