The aim of this research is an improvement of plant seedling recognition by two new approaches of shape feature generation based on plant silhouettes. Experiments show that the proposed feature sets possess value in plant recognition when compared with other feature sets. Both methods approximate a distance distribution of an object, either by resampling or by approximation of the distribution with a high degree Legendre polynomial. In the latter case, the polynomial coefficients constitute a feature set. The methods have been tested through a discrimination process where two similar plant species are to be distinguished into their respective classes. The used performance assessment is based on the classification accuracy of 4 different classifiers (a k-Nearest Neighbor, Naive-Bayes, Linear Support Vector Machine, Nonlinear Support Vector Machine). Another set of 21 well-known shape features described in the literature is used for comparison. The used data consisted of 139 samples of cornflower (Centaura cyanus L.) and 63 samples of nightshade (Solanum nigrum L.). The highest discrimination accuracy was achieved with the Legendre Polynomial feature set and amounted to 97.5%. This feature set consisted of 10 numerical values. Another feature set consisting of 21 common features achieved an accuracy of 92.5%. The results suggest that the Legendre Polynomial feature set can compete with or outperform the commonly used feature sets.
References
[1]
Brown, R.B.; Noble, S.D. Symposium Site-specific weed management: Sensing requirements—what do we need to see? Weed Sci. 2005, 53, 252–258.
[2]
Woebbecke, D.M.; Meyer, G.E.; von Bargen, K.; Mortensen, D.A. Color indices for weed identification under various soil, residue, and lighting conditions. Trans. Am. Soc. Agric. Eng. 1995, 38, 259–269.
[3]
Meyer, G.; Neto, J. Verification of color vegetation indices for automated crop imaging applications. Comput. Electron. Agric. 2008, 63, 282–293.
[4]
Otsu, N. A threshold selection method from gray-level histogram. IEEE Trans. Syst. Man Cybern. 1978, C, 62–66.
[5]
Woebbecke, D.M.; Meyer, G.E.; von Bargen, K.; Mortensen, D.A. Shape features for identifying young weeds using image analysis. Trans. Am. Soc. Agric. Eng. ASAE 1995, 38, 271–281.
[6]
Lee, W.S.; Slaughter, D.C.; Giles, D.K. Robotic weed control system for tomatoes. Precis. Agric. 1999, 1, 95–113.
[7]
Hemming, J.; Rath, T. Computer-vision-based weed identification under field conditions using controlled lighting. J. Agric. Eng. Res. 2001, 78, 233–243.
[8]
Weis, M.; Gerhards, R. Feature Extraction for the Identification of Weed Species in Digital Images for the Purpose of Site-Specific Weed Control. Proceedings of the 6th European Conference on Precision Agriculture, Precision Agriculture’07, Skiathos, Greece, 3–6 June 2007; pp. 537–544.
[9]
Slaughter, D.; Giles, D.; Downey, D. Autonomous robotic weed control systems: A review. Comput. Electron. Agric. 2008, 61, 63–78.
[10]
López-Granados, F. Weed detection for site-specific weed management: Mapping and real-time approaches. Weed Res. 2011, 51, 1–11.
[11]
Dionisio, C.; Kim, H. New Features for Affine-Invariant Shape Classification. Proceedings of the International Conference on Image Processing, ICIP’04, Singapore, Singapore, 24–27 October 2004; Volume 4, pp. 2135–2138.
[12]
Mei, Y.; Androutsos, D. Robust affine invariant region-based shape descriptors: The ICA zernike moment shape descriptor and the whitening zernike moment shape descriptor. Signal Process. Lett. IEEE 2009, 16, 877–880.
[13]
Giselsson, T.M. Real Time Crops and Weeds Classification from Top Down Images of Plant Canopies. M.Sc. Thesis, University of Southern Denmark, Odense, Denmark, 2010.
[14]
Meier, U. Growth Stages of Mono-and Dicotyledonous Plants. Technical Report; Federal Biological Research Centre for Agriculture and Forestry: Berlin, Germany, 2001.
[15]
Leon, S.J. Linear Algebra with Applications; Pearson Education: Upper Saddle River, NJ, USA, 2002.
[16]
Hu, M.K. Visual pattern recognition by moment invariants. IEEE Trans. Inf. Theory 1962, 8, 179–187.
[17]
Du, J.X.; Wang, X.F.; Zhang, G.J. Leaf shape based plant species recognition. Appl. Math. Comput. 2007, 185, 883–893.
[18]
？strand, B.; Baerveldt, A. Plant Recognition and Localization Using Context Information. Proceedings of the IEEE Conference Mechatronics and Robotics—Special Session Autonomous Machines in Agriculture, Aachen, Germany, 13–15 September 2004; pp. 1191–1196.
[19]
Tian, L.; Slaughter, D.; Norris, R. Machine Vision identification of tomato seedlings for automatic weed control. Trans. ASAE 1997, 40, 1761–1768.
[20]
Peura, M.; Iivarinen, J. Efficiency of Simple Shape Descriptors. In Aspects of Visual Form; World Scientific: Singapore: Singapore, 1997; pp. 443–451.
[21]
Zhang, D.; Lu, G. Review of shape representation and description techniques. Pattern Recognit. 2004, 37, 1–19.
[22]
Pekalska, E.; Ridder, D.D.; Tax, D.M.J.; Verzakov, S. A matlab toolbox for pattern recognition. Pattern Recognit. 2007, 1, 1–61.
[23]
Giselsson, T.M.; Midtiby, H.S.; J？ rgensen, R.N. Seedling Discrimination Using Shape Features Derived from a Distance Transform. Proceedings of the 12th International Conference of Agricultural Engineering CIGR 2012, Valencia, Spain, 8–12 July 2012; p. C0406.
