Combination of gross shape features, fourier descriptors and multiscale distance matrix for leaf recognition

In this study, we have experimented with different image and shape descriptors on the automatic leaf recognition problem. We have studied the effects of gross shape descriptors, Fourier descriptors, multiscale distance descriptors, and the combination of these on the leaf recognition performance using two different datasets. We have achieved 94.62% recognition performance on Flavia, comparable to PNN 90.31%and SVM-BDT 96%. Our performance on SLID dataset, 96.67%, is comparable to MDM-A 93.60% and hierarchical matching of deformable shapes 96.28%.