Neural network segmentation of images from stained cucurbits leaves with colour symptoms of biotic and abiotic stresses

Jarosław Gocławski; Joanna Sekulska-Nalewajko; Elżbieta Kuźniak

International Journal of Applied Mathematics and Computer Science (2012)

  • Volume: 22, Issue: 3, page 669-684
  • ISSN: 1641-876X

Abstract

top
The increased production of Reactive Oxygen Species (ROS) in plant leaf tissues is a hallmark of a plant's reaction to various environmental stresses. This paper describes an automatic segmentation method for scanned images of cucurbits leaves stained to visualise ROS accumulation sites featured by specific colour hues and intensities. The leaves placed separately in the scanner view field on a colour background are extracted by thresholding in the RGB colour space, then cleaned from petioles to obtain a leaf blade mask. The second stage of the method consists in the classification of within mask pixels in a hue-saturation plane using two classes, determined by leaf regions with and without colour products of the ROS reaction. At this stage a two-layer, hybrid artificial neural network is applied with the first layer as a self-organising Kohonen type network and a linear perceptron output layer (counter propagation network type). The WTA-based, fast competitive learning of the first layer was improved to increase clustering reliability. Widrow-Hoff supervised training used at the output layer utilises manually labelled patterns prepared from training images. The generalisation ability of the network model has been verified by K-fold cross-validation. The method significantly accelerates the measurement of leaf regions containing the ROS reaction colour products and improves measurement accuracy.

How to cite

top

Jarosław Gocławski, Joanna Sekulska-Nalewajko, and Elżbieta Kuźniak. "Neural network segmentation of images from stained cucurbits leaves with colour symptoms of biotic and abiotic stresses." International Journal of Applied Mathematics and Computer Science 22.3 (2012): 669-684. <http://eudml.org/doc/244060>.

@article{JarosławGocławski2012,
abstract = {The increased production of Reactive Oxygen Species (ROS) in plant leaf tissues is a hallmark of a plant's reaction to various environmental stresses. This paper describes an automatic segmentation method for scanned images of cucurbits leaves stained to visualise ROS accumulation sites featured by specific colour hues and intensities. The leaves placed separately in the scanner view field on a colour background are extracted by thresholding in the RGB colour space, then cleaned from petioles to obtain a leaf blade mask. The second stage of the method consists in the classification of within mask pixels in a hue-saturation plane using two classes, determined by leaf regions with and without colour products of the ROS reaction. At this stage a two-layer, hybrid artificial neural network is applied with the first layer as a self-organising Kohonen type network and a linear perceptron output layer (counter propagation network type). The WTA-based, fast competitive learning of the first layer was improved to increase clustering reliability. Widrow-Hoff supervised training used at the output layer utilises manually labelled patterns prepared from training images. The generalisation ability of the network model has been verified by K-fold cross-validation. The method significantly accelerates the measurement of leaf regions containing the ROS reaction colour products and improves measurement accuracy.},
author = {Jarosław Gocławski, Joanna Sekulska-Nalewajko, Elżbieta Kuźniak},
journal = {International Journal of Applied Mathematics and Computer Science},
keywords = {image segmentation; colour space; morphological processing; image thresholding; artificial neural network; WTA learning; Widrow-Hoff learning; Cucurbita species; plant stress; ROS detection; cucurbita species},
language = {eng},
number = {3},
pages = {669-684},
title = {Neural network segmentation of images from stained cucurbits leaves with colour symptoms of biotic and abiotic stresses},
url = {http://eudml.org/doc/244060},
volume = {22},
year = {2012},
}

TY - JOUR
AU - Jarosław Gocławski
AU - Joanna Sekulska-Nalewajko
AU - Elżbieta Kuźniak
TI - Neural network segmentation of images from stained cucurbits leaves with colour symptoms of biotic and abiotic stresses
JO - International Journal of Applied Mathematics and Computer Science
PY - 2012
VL - 22
IS - 3
SP - 669
EP - 684
AB - The increased production of Reactive Oxygen Species (ROS) in plant leaf tissues is a hallmark of a plant's reaction to various environmental stresses. This paper describes an automatic segmentation method for scanned images of cucurbits leaves stained to visualise ROS accumulation sites featured by specific colour hues and intensities. The leaves placed separately in the scanner view field on a colour background are extracted by thresholding in the RGB colour space, then cleaned from petioles to obtain a leaf blade mask. The second stage of the method consists in the classification of within mask pixels in a hue-saturation plane using two classes, determined by leaf regions with and without colour products of the ROS reaction. At this stage a two-layer, hybrid artificial neural network is applied with the first layer as a self-organising Kohonen type network and a linear perceptron output layer (counter propagation network type). The WTA-based, fast competitive learning of the first layer was improved to increase clustering reliability. Widrow-Hoff supervised training used at the output layer utilises manually labelled patterns prepared from training images. The generalisation ability of the network model has been verified by K-fold cross-validation. The method significantly accelerates the measurement of leaf regions containing the ROS reaction colour products and improves measurement accuracy.
LA - eng
KW - image segmentation; colour space; morphological processing; image thresholding; artificial neural network; WTA learning; Widrow-Hoff learning; Cucurbita species; plant stress; ROS detection; cucurbita species
UR - http://eudml.org/doc/244060
ER -

References

top
  1. Cheeseman, J.M. (2006). Hydrogen peroxide concentrations in leaves under natural conditions, Journal of Experimental Botany 57(10): 2435-2444. 
  2. Du Buf, H. and Bayer, M. (Eds.) (2002). Automatic Diatom Identification, World Scientific Publishing, New York, NY/London/Singapore/Hong Kong. Zbl1018.68070
  3. Forgy, E. (1965). Cluster analysis of multivariate data: Efficiency vs. interpretability of classification, Biometrics 21: 768-769. 
  4. Fukunaga, K. and Hostetler, L. (1975). The estimation of the gradient of a density function, with applications in pattern recognition, IEEE Transactions on Information Theory 21(1): 32-40. Zbl0297.62025
  5. Gonzalez, R.C. and Woods, R.E. (2008). Digital Image Processing, 3rd Edn., Prentice Hall, Upper Saddle River, NJ. 
  6. Hagan, M.T., Demuth, H. B. and Beale, M.H. (2009). Neural Network Design, University of Colorado, Denver, CO, Chapter 10, http://www.personeel.unimaas. nl/westra/Education/ANO/10widrow_hoff.pdf 
  7. Hecht-Nielsen, R. (1987). Counterpropagation networks, Applied Optics 26(23): 4979-4984. 
  8. Huang, CX-S., Liu, J-H. and Chen, X-J. (2010). Overexpression of PtrABF gene, a bZIP transcription factor isolated from Poncirus trifoliata, enhances dehydration and drought tolerance in tobacco via scavenging ROS and modulating expression of stress-responsive genes, BMC Plant Biology 10: 1-18, paper 230, http://www.biomedcentral.com/1471-2229/10/230. 
  9. James, W.C. (1971). An illustrated series of assessment keys for plant diseases, their preparation and usage, Canadian Plant Disease Survey 51(2): 39-65. 
  10. Kohonen, T. (1990). The self-organising map, Proceedings of IEEE 78(9): 1464-1479. 
  11. Kohonen, T. (2001). Self-organizing Maps, 3rd Edn., Springer-Verlag, Berlin/Heidelberg/New York, NY. Zbl0957.68097
  12. Masters, T. (1993) Practical Neural Network Recipes in C++, Academic Press Inc., San Diego, CA. Zbl0818.68049
  13. Ong, S., Yeo, N., Lee, K., Venkatesh, Y. and Cao, D. (2002). Segmentation of color images using a two-stage selforganizing network, Image and Vision Computing 20(4): 279-289. 
  14. Osowski, S. (2006). Neural Networks for Information Processing, Warsaw University of Technology Press, Warsaw, (in Polish). 
  15. Otsu, N. (1979). A threshold selection method from gray-level histograms, IEEE Transactions on Systems, Man, and Cybernetics 9(1): 62-66. 
  16. Refaeilzadeh, P., Tang, L. and Liu, H., (2009). Cross-validation, Encyclopedia of Database Systems, Springer Publishing Company, New York, NY, pp. 532-538, 
  17. Rubner, Y., Puzicha, J., Tomasi, C. and Buhmann J.M. (2001). Empirical evaluation of dissimilarity measures for color and texture, Computer Vision and Image Understanding 84(1): 25-43. Zbl1021.68787
  18. Sanders, J. and Kandrot, E. (2011). CUDA by Example: An Introduction to General-Purpose GPU Programming, Addison-Wesley, New York, NY/London. 
  19. Smith, A.R. (1978). Color gamut transform pairs, Computer Graphics 12(3): 12-19. 
  20. Soukupova, J. and Albrechtova, J. (2003). Image analysis-Tool for quantification of histochemical detection of phenolic compounds, lignin and peroxidases in needles of Norway spruce, Biologia Plantarum 46(4): 595-601. 
  21. Tabrizi, P.R., Rezatofighi, S.H. and Yazdanpanah, M.J. (2010). Using PCA and LVQ neural network for automatic recognition of five types of white blood cells, Engineering in Medicine and Biology Society (EMBC), 2010 Annual International Conference of the IEEE, Teheran, Iran, pp. 5593-5596. 
  22. Tang, Q-H., Liu, B-H., Chen, Y-Q., Zhou, X-H. and Ding, JS. (2007). Application of LVQ neural network combined with the genetic algorithm in acoustic seafloor classification, Chinese Journal Geophysics 50(1): 313-319. 
  23. The Mathworks Inc. (2011a). MEX-files guide, http://www.mathworks.com/support/tech-notes/1600/1605.html 
  24. The Mathworks Inc. (2011b). Image processing toolbox user's guide, http://www.mathworks.com//help/toolbox/images/ 
  25. Thordal-Christensen, H., Zhang, Z., Wei, Y.D. and Collinge, D.B. (1997). Subcellular localization of H₂O₂ in plants. H₂O₂ accumulation in papillae and hypersensitive response during the barley-powdery mildew interaction, Plant Journal 11(6): 1187-1194. 
  26. Unger, Ch., Kleta, S., Jandl, G. and Tiedemann, A. (2005). Suppression of the defence-related oxidative burst in bean leaf tissue and bean suspension cells by the necrotrophic pathogen Botrytus cinerea, Journal of Phytopathology 153(1): 15-26. 
  27. Wijekoon, C.P., Goodwin, P.H. and Hsiang, T. (2008). Quantifying fungal infection of plant leaves by digital image analysis using Scion Image software, Journal of Microbiological Methods 74(2-3): 94-101. 
  28. Widrow, B., Winter, R.G. and Baxter, R.A. (1988). Layered neural nets for pattern recognition, IEEE Transactions on Acoustics, Speech and Signal Processing 36(7): 1109-1118. Zbl0652.68102

NotesEmbed ?

top

You must be logged in to post comments.

To embed these notes on your page include the following JavaScript code on your page where you want the notes to appear.

Only the controls for the widget will be shown in your chosen language. Notes will be shown in their authored language.

Tells the widget how many notes to show per page. You can cycle through additional notes using the next and previous controls.

    
                

                
Note: Best practice suggests putting the JavaScript code just before the closing </body> tag.