Chili Classification Using Shape and Color Features Based on Image Processing

Abstract. Purpose: Chili is an agricultural product that has several varieties and in great demand. It can be consumed directly or processed first. This study aims to classify the types of chili using color shape features. The are divided into five classes: cayenne pepper, green chili, big red curly chili. classification method was evaluated three parameters: precision, recall, accuracy.Methods: applied K-Nearest Neighbors (KNN) with Euclidean Manhattan distance calculation algorithm used two feature types: shape. features were extracted based on RGB space by obtaining mean standard deviation values. Meanwhile, aspect ratio, area, boundary.Result: evaluation results able achieve accuracy values 1.0, which means all test data classified correctly. 210 training images 90 results.Novelty: features: Those fed KNN applying algorithm; hence, optimal achieved.