<![CDATA[This study aims to determine the extent to which the KNN algorithm is able to classify pineapple fruit based on color features with high accuracy and determine the best k value in the KNN algorithm to achieve optimal accuracy in the classification of pineapple maturity levels. In the process of classifying pineapple fruit manually by using the human eye is a very difficult thing to do. This is evidenced by the inconsistency and subjective nature that causes a low level of accuracy. Therefore, to increase the level of accuracy and reduce the subjectivity of the human eye, this research proposes an algorithm that can be used to classify the maturity level of pineapple fruit, namely with K-Nearest Neighbor based on the color of the skin on the fruit. The k value used in this research is 1, 3, 5, 7, and 9 to test the Euclidean distance search on images with a size of 300x300 pixels. The research conducted proves that with Euclidean distance k = 5 and k = 9 has a percentage value of 73%. Based on the level of accuracy, color features k = 5 and k = 9 show the best k value on the classification of pineapple ripeness level.]]>
Copyrights © 2024
