<![CDATA[Papaya fruit is one of the kings of fruit in Indonesia. It is said to be the king of fruit because it is rich in benefits and has good nutritional and vitamin content. Grouping the maturity of papaya fruit is very important. The difficulty in clarifying the ripeness of papaya fruit is based on its color features, and the grouping of papaya fruit ripeness is divided into several categories, namely ripe, semi-ripe and unripe. This research aims to predict the level of ripeness of papaya fruit using the K-Nearest Neighbor method using features obtained from extraction results with RGb and HSI images. The system that has been created can classify papaya fruit images into raw, semi-ripe and ripe classes. Programming includes identifying needs, analyzing problems, selecting algorithms, and determining the data structure to be used. The aim of program design is to create a good and effective design before starting to implement the program. The first stage is to design the program using the GUI tool from the Matlab application. In the second stage, the source code must be entered so that the program can be run. Papaya fruit samples that were tested for ripeness were obtained from taking images using several smartphone cameras and at different times. Some were taken during the day, some at night. Table 4. Shows that all of the images of papaya fruit samples are in accordance with the application of papaya ripeness levels. With test results showing that test accuracy reaches a perfect level of 100%. This indicates that the testing system used is able to accurately detect the ripeness of papaya fruit. The use of the K-Nearst Neighbor (K-NN) method has been successfully carried out in this research.]]>
