Plant Leaf Identification Using Gabor Wavelets

This article presents a novel method of plant classification using Gabor wavelet filters to extract texture filters in a foliar surface. The aim of this promising method is to add to the results obtained by other leaf attributes (such as shape, contour, color, among others), increasing, therefore, the percentage of classification of plant species. To corroborate the efficiency of the technique, an experiment using 20 species from Brazilian flora was done and discussed. The results are also compared with texture Fourier descriptors and cooccurrence matrices. (C) 2009 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 19, 236-243, 2009; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/ima.20201

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

CNPq (National Council for Scientific and Technological Development, Brazil)[306628/2007-4]

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

CNPq (National Council for Scientific and Technological Development, Brazil)[135251/2006]

FAPESP (The State of Sao Paulo Research Foundation)[2006/53972-6]

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

FAPESP (The State of Sao Paulo Research Foundation)[2008/57313-2]