Tropical rainforest has more than 3,000 different types of timber species, out of these, about 200 species are being used by the timber industry. The properties of these bamboo species varies a lot and different species are recommended for different purpose. Due to this fact, recognition of bamboo species is necessary before its efficient utilization. Due to unavailability of the database,the databse is developed in Forest Research institute Dehradun by collecting the raw samples of Culm sheath. The three moment based classification techniques ie. Central moment Legendre moment and Fourier moment is adopted to perform the experiment. The performqance of these techniques is measured by introducing three paprameter i.e classwise classification accuracy,overall classifier accuracy and computation time. A confusion matrix is created to quantify the class wise and classifier accuracy. The results show that the Fourier Moment has to be superior classification accuracy compared to Legendre and central moment, and computation time is very low,because only boundary points are consider for calculating the moment. This application can eliminate the need for laborious human recognition method requiring a plant taxonomist. The results obtained shows considerable recognition accuracy proving that the techniques used is suitable to be implemented for commercial purposes. © 2012 Springer-Verlag GmbH Berlin Heidelberg.
CITATION STYLE
Singh, K., & Singh, S. (2012). Comparisons of three classifier for classification of bamboo plant. In Advances in Intelligent and Soft Computing (Vol. 132 AISC, pp. 795–802). Springer Verlag. https://doi.org/10.1007/978-3-642-27443-5_91
Mendeley helps you to discover research relevant for your work.