Classification Of Guarantee Fruit Murability Based on HSV Image With K-Nearest Neighbor

Frencis Matheos Sarimole (Sekolah Tinggi Ilmu Komputer Cipta Karya Informatika)
Muhammad Ilham Fadillah (Sekolah Tinggi Ilmu Komputer Cipta Karya Informatika)

Journal of Applied Engineering and Technological Science (JAETS)
Vol. 4 No. 1 (2022): Journal of Applied Engineering and Technological Science (JAETS)

Guava bol is one of the fruits from Indonesia that is favored by many Indonesian people. The guava itself has a soft and dense flesh texture compared to water guava. The guava itself has a pink color if it is raw but if the guava is ripe it will be dark red. From a glance, when viewed from human vision, it is very easy to distinguish between them, but from most people it is still difficult to distinguish which guava is ripe, half-ripe and unripe guava because of differences in opinion from one human eye to another. Based on these problems, researchers have developed a system that is able to detect the maturity level of guava fruit by utilizing the Hue Saturation Value (HSV) feature extraction with K-Nearest Neighbor (KNN). The data used in this study were 465 datasets which were divided into 324 training data and 141 test data. The data had classes, namely ripe, half-cooked, and raw. The data is then classified using the K-Nearest Neighbor method by calculating the closest distance with a value of K = 3. From this study resulted in an accuracy of 97.16%.