Identifikasi tanaman hias secara otomatis menggunakan Metode Local Binary Patterns descriptor dan Probabilistic Neural Network

Abstract

Identification house plant species automatically still be a problem for recognizing various kind of house plants. This research proposes a new method for identifying a house plant using Local Binary Patterns (LBP) descriptor and Probabilistic Neural Network (PNN). There are three kinds of LBP descriptor used in this research, i.e. , , and . Database of 300 house plant images belong to 30 different types of house plant in Indonesia are extracted using , , and based on texture feature and classified using PNN. The experimental result shows that has the best accuracy to indentify house plants with accuracy 73.33%. The proposed system is promising since it is capable to identify house plants species efficienty and accurately