Open AccessKlasifikasi Kematangan Stroberi Berbasis Segmentasi Warna dengan Metode HSV
Author(s) -
Intan Sari Areni,
Indrabayu Amirullah,
Nurhikma Arifin
Publication year - 2019
Publication title -
jurnal penelitian enjiniring fakultas teknik unhas
Language(s) - English
Resource type - Journals
eISSN - 2685-4104
pISSN - 1411-6243
DOI - 10.25042/jpe.112019.03
Subject(s) - artificial intelligence , hue , rgb color model , hsl and hsv , support vector machine , computer science , pattern recognition (psychology) , color space , kernel (algebra) , mathematics , computer vision , image (mathematics) , biology , virus , virology , combinatorics
Classification of Strawberry Maturity Based on Color Segmentation using HSV Method. Manual fruit maturity classification has many limitations because it is influenced by human subjectivity. Hence, the application of digital image processing and artificial intelligence becomes more effective and efficient. This study aims to create a classification system that automatically divides strawberry maturity into three categories, namely not ripe, half-ripe, and ripe. The process of identifying the level of fruit maturity is based on the color characteristics Red, Green, Blue (RGB) value of the image. The method used for color segmentation is Hue, Saturation, Value (HSV) and for the classification of strawberry maturity using the Multi-Class Support Vector Machine (SVM) algorithm with a Radial Basic Function (RBF) kernel. Strawberry image data was retrieved using the Logitech C920 camera. The dataset consisted of 158 images of strawberries. The results showed that the classification of strawberry maturity using the multi-class SVM algorithm with kernel parameters RBF cost (C) = 10 and gamma (γ) = 10-3 produced the highest accuracy of 97%.