Identifikasi Jenis Daun Tanaman Obat Berdasarkan Fitur Tekstur Menggunakan LVQ

Prasetyo, Aji Wahyu (2021) Identifikasi Jenis Daun Tanaman Obat Berdasarkan Fitur Tekstur Menggunakan LVQ. Diploma thesis, Politeknik Negeri Jember.

	Text (Abstract) ABSTRACT.pdf - Submitted Version Available under License Creative Commons Attribution Share Alike. Download (296kB)
	Text (Bab 1 Pendahuluan) BAB 1.pdf - Submitted Version Available under License Creative Commons Attribution Share Alike. Download (1MB)
	Text (Daftar Pustaka) DAFTAR PUSTAKA.pdf - Submitted Version Available under License Creative Commons Attribution Share Alike. Download (724kB)
	Text (Laporan Lengkap) Laporan Lengkap.pdf - Submitted Version Restricted to Repository staff only Download (3MB) | Request a copy

Abstract

Medicinal plants are plants containing active substances that function to treat certain diseases or if they do not contain certain active substances but contain resultant or synergistic effects of various substances that function to treat. Medicinal plants themselves are types of plants that are used every part of it starting from the leaves, stems, roots, flowers, fruits and even the seeds can also be used as very useful medicine. To find out the types of medicinal plants that are most often used in the identification process of medicinal plants, namely the leaves. To determine the characteristics of the leaves of medicinal plants obtained from the feature extraction used, namely the extraction of shape features and extraction of texture features. The results will be classified into 4 classes using the Learning Vector Quantization method. results Based on the test of the training data obtained a value of 95,5% using a learning rate of 0,1 and a decrease in the learning rate of 0,75, for the test results from the test data obtained 95% accuracy by using a learning rate of 0,1 and a decrease in the learning rate of 0,75. This shows that the Learning Vector Quantization method is good enough to classify the types of medicinal plant leaves.

Actions (login required)

View Item