Klasifikasi Citra Daun Herbal Dengan Menggunakan Backpropagation Neural Networks Berdasarkan Ekstraksi Ciri Bentuk
Arief Herdiansah, Rohmat Indra Borman, Desi Nurnaningsih, Alfry Aristo Jansen Sinlae, Rosyid Ridlo Al Hakim
Abstract
Since ancient times until now herbal plants have been used for treatment and have been applied in the world of health to this day. All parts of the plant can be used as medicine, one of which is the leaves. However, there are still many people who are not familiar with the medicinal leaves. This is because the leaves at first glance look almost the same, making it difficult to tell them apart. Actually, if you look closely, the leaves have characteristics that can be distinguished from one leaf to another. The purpose of this study is to classify images of herbal leaf species using the Backpropagation Neural Network (BNN) algorithm with shape feature extraction utilizing metric and eccentricity parameters. BNN is a type of supervised learning algorithm that consists of several layers and uses an error output as a modifier of the weight value backwards. In this study, the extraction of shape features that become input for the BNN algorithm will go through morphological operations to improve the segmentation results so that the classification results are more optimal. The test results show an accuracy of 88.75%, this shows the developed model can classify herbal leaves well