Classification of Apples using Machine Learning
Agus Pratondo, Devira M. A. Harahap
Abstract
Apple classification is needed in various automation in the agricultural product processing industry. Classification of a small number of apples is very easy for humans to do, but in large numbers, manual work becomes less reliable. This study aims to build a model that can be used for automatic apple classification. The model is built using classification algorithms, namely k-nearest neighbors and support vector machine. A number of images on the apple variant, named envy, fuji, malang, and gala, were used for learning. The images are converted to grayscale and resized to a certain size for computational efficiency. The experimental results show that the accuracy of the model in recognizing the apple image reaches 94.00 % and 94.50% for the k-nearest neighbors and support vector machine, respectively. These results are quite promising for use in various applications related to apple classification.