Red Chili Classification Using HSV Feature Extraction and Naive Bayes Classifier

Abstract

In the culinary industry, the classification of red chili pepper types is used to identify varieties that differ in terms of flavor, pungency, or other uniqueness. This enables their proper use in various recipes and meals. In the market, the classification of red chili pepper types helps in pricing, variety selection, or quality standards applied. For this reason, the purpose of this research is to classify red chili peppers using HSV Feature Extraction and Naive Bayes Clasifier. The stages carried out include: data collection, preprocessing, feature extraction and classification. Red chilies are grouped into 4 classes, namely large red chilies, cakplak red chilies, curly red chilies and chili red chilies. The red chili data used is 119 training data and 123 testing data. In the preprocessing, the image is converted to grayscale, then converted to binary image with the thresholding method. Furthermore, feature extraction is done with the HSV method. Finally, classification is done with Naive Bayes. The results of the study provide an accuracy value for training data of 92.43% and for testing data obtained an accuracy of 92.69%. This method is suitable for use in classification because it gives good results