Gerga Orange Quality Using Naïve Bayes Based on Feature Extraction

In an effort to increase the number of sales, process classifying type Gerga citrus fruit is very necessary. The problem that often occurs mixing various types from storage warehouse so quality will be mixed and it difficult determine selling price because itself not evenly distributed a sorting needed. There are still many sellers or growers fruits who sort manually can take long time. Given these problems, necessary classify oranges automatically with Naïve Bayes Classifier algorithm GLCM feature extraction HSV color characteristics. as method for media used, there digital image media. From experiments have been carried out use angles in formation co-occurrence matrices best accuracy values reaching 80% found at 0°, 45°, 135°, while lowest 90°. It was concluded classification system using categorized good AUC value 0.8.