Abstract
A new neural network architecture for classification purposes is proposed. The Self-Organizing Map (SOM) neural network is used in a supervised way for a classification task. The neurons of the SOM become associated with local linear mappings (LLM). Error information obtained during training is used in a novel learning algorithm to train the classifier. The proposed method achieves fast convergence and good generalization. The classification method is then applied in a precision farming application, the classification of crops and different kinds of weeds by using spectral reflectance measurements. The classification performance of the proposed method is proven superior compared to other neural classifiers. Also, the proposed method compares favorably with the results obtained by using an optimal Bayesian classifier.
Similar content being viewed by others
References
Bennet K. A. and Brown, R. B. 1997. Direct nozzle injection and precise metering for variable rate herbicide application, Paper No. 97–1046 (American Society of Agricultural Engineers, St. Joseph, MI, USA).
Biller, R. H. 1998. Reduced input of herbicides by use of optoelectronic sensors. Journal of Agricultural Engineering Research 71, 357–362.
Bishop, C. M. 1995. Neural Networks for Pattern Recognition (Oxford University Press, Oxford, U.K.).
Chancellor, W. J. and Goronea, M. A. 1993. Spatial variability of nitrogen, moisture and weeds, Paper No. 93–1069 (American Society of Agricultural Engineers, St. Joseph, MI, USA).
Dietterich, T. G. 1997. Approximate statistical tests for comparing supervised classification learning algorithms. Neural Computation 10(7), 1895–1924
Efron, B. and Gong, G. 1983. A leisurely look at the bootstrap, the jacknife and cross-validation. The American Statistician 37(1), 36–48.
Everitt, B. S. 1977. The Analysis of Contingency Tables (Chapman and Hall, London).
Gausman, H. W. 1985. Plant leaf optical properties in visible and near-infrared light, Dissertation (Texas Tech University, 78 pp., Lubbock, Texas, USA).
Grant, L. 1987. Diffuse and specular characteristics of leaf reflectance. Remote Sensing of the Environment 22, 309–322.
Hahn, F. and Muir, A. Y. 1993. Weed-Crop discrimination by optical reflectance. In: Proceedings of IV International Symposium on Fruit, Nut, and Vegetable Production Engineering, edited by F. Juste (Ministerio de Agriculture, Pesca y Alimentación & INIA, Valencia, Spain), vol. 1, p. 221–228.
Herrala, E., Okkonen, J., Hyvarinen, T., Aikio M. and Lammasniemi, J. 1994. Imaging spectrometer for process industry applications. SPIE 2248, 33–40.
Kohonen, T. 1982. Self-organized formation of topologically correct feature maps. Biological Cybernetics 43, 59–69.
Kohonen, T. 1995. Self-Organizing Maps, Springer Series in Information Sciences (Springer Verlag Berlin-Heidelberg).
Miller, P. C. H. and Stafford, J. V. 1991. Herbicide application to targetted patches. In: Brighton Crop Protection Conference—Weeds—1991 (British Crop Protection Council, Brighton), vol. 3, p. 1249–1256.
Moshou, D., De Ketelaere, B., Vrindts, E., De Baerdemaeker, J. and Ramon, H. 1998. Local linear mapping neural networks for pattern recognition of plants. In: Proceedings of First IFAC/CAEA, International Workshop on Control Applications and Ergonomics in Agriculture, June 4–6 1998 (Athens, Greece) p. 61–66.
Niles, L., Silverman, H., Tajchman, G. and Bush, M. 1989. How limited training data can allow a neural network to outperform an 'optimal' statistical classifier. In: Proceedings of International Conference on Acoustics, Speech, and Signal Processing '89 (editor IEEE, New York) p. 17–20.
Ritter, H., Martinetz, T. and Schulten, K. 1992. Neural Computation and Self-Organizing Maps: An Introduction (Addison-Wesley, New York).
Rosenblatt, M. 1956. Remarks on some nonparametric estimates of a density function. Annals of Mathematical Statistics 27, 832–837.
Rumelhart, D. E., Hinton, G. E. and Williams, R. J. 1986. Parallel Distributed Processing (MIT Press, Cambridge, USA), vol. 1, p. 318–362.
Specht, D. F. 1990. Probabilistic neural networks. Neural Networks 3(1), 109–118.
Stafford, J. V. and Benlloch, J. V. 1997. Machine-assisted detection of weeds and weed patches. In: Precision Agriculture '97, Proceedings of the First European Conference on Precision Agriculture, edited by J. V. Stafford (Bios Scientific Publishers, Oxford, UK), p. 511–518.
Vrindts, E. and De Baerdemaeker, J. 1997. Optical discrimination of crop, weed and soil for on-line weed detection. In: Proceedings of the First European Conference on Precision Agriculture, edited by J. Stafford (BIOS Scientific Publishers, Oxford, UK), p. 537–544.
Vrindts, E. and De Baerdemaeker, J. 1999. Optical weed detection and evaluation using reflection measurements. In: Precision Agriculture and Biological—Quality. Proceedings of SPIE, vol. 3543; 3–4 Nov. 1998, Boston, USA edited by G. E. Meyer and J. A. DeShazer (Bellingham, Washington, USA), p. 279–289.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Moshou, D., Ramon, H. & De Baerdemaeker, J. A Weed Species Spectral Detector Based on Neural Networks. Precision Agriculture 3, 209–223 (2002). https://doi.org/10.1023/A:1015590520873
Issue Date:
DOI: https://doi.org/10.1023/A:1015590520873