Classification of Lycopersicon Esculentum Fruit Based on Color Features with Linear Discriminant Analysis (LDA) Method

摘要

Tomatoes (Lycopersicon Esculentum) is a fruit that has many types. One way to distinguish the types of tomatoes can be seen from differences in color, size, and shape. To assist in the classification of tomatoes, a study was conducted which aims to classify two types of tomatoes namely plum tomatoes and beef tomatoes. Therefore, the processing of tomato images is done to facilitate the layman in classifying the two types of tomatoes. The research method used consisted of preprocessing in the form of color conversion l*a*b and HSV for feature extraction, and Linear Discriminant Analysis (LDA) method used to determine data distribution. This method can separate and classify the two types of tomatoes well. The use of adequate training data will further improve classification accuracy. The final results of this study indicate that the level of accuracy in the classification of tomatoes for both types is 90%.