Identifikasi Citra Daun Menggunakan Probabilistic Neural Network, Radial Basis Neural Network, dan Support VectorMechine

Abstract

This research proposes a system for leaf identification using three classifiers: Probabilistic Neural Network (PNN), Radial Basis Neural Network (RBFNN) and Support Vector Machine (SVM). The features that used for classification are morphology, texture, and shape of leaves. Those features are combined by joining all feature matrices. The method to extract texture and shape is co-occurrence matrix and Fourier descriptors, respectively. After feature extraction, the feature is classified using PNN, RBFNN and SVM. The experiment data consists of thirty species flora from Bogor Botanical Garden, Indonesia. The experimental results show that all of leaf features (morphology, texture, and shape) are important for leaf identification. The best system accuration is shown by PNN with 79.05%.