Perbandingan Klasifikasi Citra Daun Herbal Menggunakan Metode Logistic Regression dan Decision Tree Classifier Berdasarkan Fitur (Warna, GLCM, Bentuk)

Abstract

The development of plant science is growing rapidly regarding herbal plants. Herbs have many benefits for life to prevent, cure diseases. To find out the types of herbal plants is done by the classification process. Classification of herbal plants can be done by identifying the shape of the leaf image of herbal plants by extracting color features, GLCM and shape from herbal leaves. The 275 dataset consists of 25 leaf types with 11 total datasets. There are several kinds of classification methods that can be used. In this study, the classification methods used were the Logistic Regression and Decision Tree Classifier methods. Based on the results of trials conducted using the Logistic Regression method, the train classification accuracy value was 72.9% and the classification test accuracy was 60.24%, while the Decision Tree Classifier method had a train classification accuracy value of 100% and the accuracy of the classification test was 78.31. This shows that the performance of the Decision Tree Classifier method is better than the Logistic Regression method