Implementation of HSI and LBP Feature Extraction for Identification of Broccoli Quality with F-KNN

This study proposes a method of searching for broccoli quality based on imagery using the Fuzzy K-nearest neighbor (F-KNN). Broccoli is used because it is a type of herbaceous vegetable that has a unique color and shape so visual assessment is still limited. The data used in this study were taken from 2 cities in Indonesia, Pasuruan and Malang Regency which consisted of good quality and bad quality. The total data used is 120, each quality comprising 60 images. In the pre-processing process, several stages are carried out to proceed to the next process. Feature extraction is done through algorithms, namely HSI (Hue, Saturation, and Intensity) and LBP (Local Binary Pattern), which are then divided into training and testing data. F-KNN is used as a classification. The accuracy obtained from this study reached 94.4%. This value indicates that the use of both feature extraction and classification algorithms produces good accuracy in the training and testing data with a 40:60 scenario. This result showed the potential of the feature extraction and F-KNN algorithm when classifying a large number of broccoli qualities.