Klasifikasi Kematangan Sayuran Pare dengan Metode KNN

Abstract

The bitter melon plant (Momordica charantia L) is a vegetable commodity that has commercial potential if cultivated on an agribusiness scale. The bitter melon plant products currently have quite a lot of consumers and have even entered supermarkets. However, the selection of bitter melon vegetables still uses human eye assessment which has the weakness of being subjective and inconsistent, so the level of accuracy is low. Based on these problems, researchers will create a system that is able to classify the level of maturity of bitter melon vegetables using HSV feature extraction with the KNN method at the classification stage and with the help of the Python programming language. In this research, 160 datasets will be used which are divided into 3 types of classes, namelcategy cooked bitter melon vegetables and raw bitter melon vegetables. The dataset is divided into two ories, namely 128 training data and 32 test data. The next stage is testing the data using the K-Nearest Neighbor method using the value k=3. From the test results, an accuracy rate of 88% was obtained.

Keywords: Python, Kematangan, Pare, KNN, HSV