Penggabungan Fitur Morfologi, Local Binary Pattern Variance, dan Color Moments untuk Aplikasi Mobile Identifikasi Citra Tumbuhan Obat

Abstract

This research proposed a new Android mobile application for medicinal plants identification using some features of leaf, i.e. texture, shape, and color. This research used 51 species of medicinal plants and each species consists of 48 images, so the total images used in this research are 2448 images. Local Binary Pattern Variance (LBPV) is used to extract the texture, morphological feature is used to extract the shape, and color moments is used to extract color feature based on color distribution. Further research was conducted on the combination of features to get a better result in medicinal plants identification. The combination technique used is the Product Decision Rule (PDR). This research uses the Probabilistic Neural Network (PNN) technique to classify the morphological, LBPV, and color moments features vector. The experimental results show that the combination of the morphological, LBPV, and color moments features can improve the accuracy of medicinal plants identification. The accuracy of the combination of the morphological, LBPV, and color moments features is 72.16%.