{"title":"On Combining Support Vector Machines and Fuzzy K-Means in Vision-based Precision Agriculture ","authors":"A. Tellaeche, X. P. Burgos-Artizzu, G. Pajares, A. Ribeiro","volume":4,"journal":"International Journal of Computer and Information Engineering","pagesStart":844,"pagesEnd":850,"ISSN":"1307-6892","URL":"https:\/\/publications.waset.org\/pdf\/6906","abstract":"One important objective in Precision Agriculture is to minimize the volume of herbicides that are applied to the fields through the use of site-specific weed management systems. In order to reach this goal, two major factors need to be considered: 1) the similar spectral signature, shape and texture between weeds and crops; 2) the irregular distribution of the weeds within the crop's field. This paper outlines an automatic computer vision system for the detection and differential spraying of Avena sterilis, a noxious weed growing in cereal crops. The proposed system involves two processes: image segmentation and decision making. Image segmentation combines basic suitable image processing techniques in order to extract cells from the image as the low level units. Each cell is described by two area-based attributes measuring the relations among the crops and the weeds. From these attributes, a hybrid decision making approach determines if a cell must be or not sprayed. The hybrid approach uses the Support Vector Machines and the Fuzzy k-Means methods, combined through the fuzzy aggregation theory. This makes the main finding of this paper. The method performance is compared against other available strategies. ","references":"[1] J.V Stafford, \"The role of technology in the emergence and current\r\nstatus of precision agriculture\" in Handbook of precision agriculture. (A.\r\nSrinivasan Ed.). Food Products Press. New York. pp 19-56, 2006.\r\n[2] A. Zhang, M. Wang and N. Wang, \"Precision Agricuture-a worldwide\r\noverview,\" Computers and Electronics in Agriculture, vol. 36, pp. 113-\r\n132, 2002.\r\n[3] R. Gerhards and H. Oebel, \"Practical experiences with a system for sitespecific\r\nweed control in arable crops using real-time image analysis and\r\nGPS-controlled patch spraying,\" Weed Research, vol. 46, pp. 185-193,\r\n2006.\r\n[4] A.J. P\u00e9rez, F. L\u251c\u2502pez, J.V. Benlloch and S. Christensen, \"Colour and\r\nShape Analysis techniques for weed detection in cereal fields,\"\r\nComputers and Electroncis in Agriculture, vol. 25, pp. 197-212, 2000.\r\n[5] H.T. S\u251c\u00a9gaard and H.J. Olsen, \"Determination of crop rows by image\r\nanalysis without segmentation,\" Computers and Electronics in\r\nAgriculture, vol. 38, pp. 141-158, 2003.\r\n[6] C.C. Yang, S.O. Prasher, J.A. Landry and H.S. Ramaswamy,\r\n\"Development of an image processing system and a fuzzy algorithm for\r\nsite-specific herbicide applications,\" Precision Agriculture, vol. 4, pp.\r\n5-18, 2003.\r\n[7] K.R. Thorp and L.F. Tian, \"A Review on Remote Sensing of Weeds in\r\nAgriculture,\" Precision Agriculture vol. 5, pp. 477-508, 2004.\r\n[8] A. Ribeiro, C. Fern\u251c\u00edndez-Quintanilla, J. Barroso and M.C. Garc\u251c\u00a1a-\r\nAlegre, \"Development of an image analysis system for estimation of\r\nweed,\". in Proc. 5th European Conf. On Precision Agriculture (5ECPA),\r\n2005 pp. 169-174\r\n[9] J. Barroso, C. Fern\u251c\u00edndez-Quintanilla, C. Ruiz, P. Hernaiz, L.J Rew,\r\n\"Spatial stability of Avena sterilis ssp. Ludoviciana populations under\r\nannual applications of low rates of imazamethbenz,\" Weed Research,\r\nvol. 44, pp. 178-186, 2004.\r\n[10] L. Radics, M. Glemnitz, J. Hoffmann, G. Czimber, \"Composition of\r\nweed floras in different agricultural management systems within the\r\nEuropean climatic gradient,\" in Proc. 6th European Weed Research\r\nSociety (EWRS). Workshop on Physical and Cultural Weed Control,\r\nLillehammer, Norway, 2004, pp. 58-64.\r\n[11] M.J. Aitkenhead, I.A. Dalgetty, C.E. Mullins, A.J.S. McDonald, N.J.C.\r\nStrachan, \"Weed and crop discrimination using image analysis and\r\nartificial intelligence methods,\" Computers and Electronics in\r\nAgriculture, vol. 39, pp. 157-171, 2003.\r\n[12] P.M. Granitto, P.F. Verdes, H.A. Ceccatto, \"Large-scale investigation of\r\nweed seed identification by machine vision,\" Computers and Electronics\r\nin Agriculture vol. 47, pp. 15-24, 2005.\r\n[13] C.M. Onyango and J.A. Marchant, \"Segmentation of row crop plants\r\nfrom weeds using colour and morphology,\" Computers and Electronics\r\nin Agriculture, vol. 39, pp. 141-155, 2003.\r\n[14] L.F. Tian, D.C. Slaughter, \"Environmentally adaptive segmentation\r\nalgorithm for outdoor image segmentation,\" Computers and Electronics\r\nin Agriculture, vol. 21, pp. 153-168, 1998.\r\n[15] J. Kapur, P. Sahoo, A. Wong, \"A new method for gray-level picture\r\nthresholding using the entropy of the histogram,\" Computer Vision\r\nGraphics Image Processing, vol. 29, n\u00ba 3, pp. 273-285, 1985.\r\n[16] P.L. Rosin, E. Ioannidis, \"Evaluation of global image thresholding for\r\nchange detection,\" Pattern Recognition Letters, vol. 24, pp. 2345-2356,\r\n2003.\r\n[17] B. Bacher, Weed density estimation from digital images in spring barley,\r\nPhD thesis, Dpt. Agricultural Sciences, Section of AgroTechnology, The\r\nRoyal Veterinary and Agricultural University, Denmark, 2001\r\n[18] R.C. Gonzalez, R.E. Woods and S.L. Eddins, Digital Image Processing\r\nusing Matlab. Prentice Hall, New York, 2004.\r\n[19] B. Astrand, A.J. Baerveldt, \"An Agricultural Mobile Robot with Vision-\r\nBased Perception for Mechanical Weed Control,\" Autonomous Robots,\r\nvol.13, pp. 21-35, 2002.\r\n[20] R.P.W Duin, \"On the choice of smoothing parameters for Parzen\r\nestimators of probability density functions,\" IEEE Trans. Comput., vol.\r\nC-25, pp. 1175-1179, 1976.\r\n[21] R.O. Duda, P.E. Hart, D.G. Stork, Pattern Classification, Jhon Willey\r\nand Sons, New York ,2001.\r\n[22] V. Cherkassky, F. Mulier, Learning from data: concepts, theory and\r\nmethods, Wiley, New York, 1998\r\n[23] V.N. Vapnik, The nature of statistical learning theory, Springer-Verlag,\r\nNew York, 2000.\r\n[24] H.J. Zimmermann, Fuzzy Set Theory and its Applications, Kluwer\r\nAcademic Publishers, Norwell, 1991.\r\n[25] P. Sneath, R. Sokal, Numerical Taxonomy: the principle and practice of\r\nnumerical classification, W.H. Freeman, 1973.","publisher":"World Academy of Science, Engineering and Technology","index":"Open Science Index 4, 2007"}