A modification of the Distance Formula on the K-Nearest Neighbor Method is Examined in Order to Categorize Spices from Photo Using the Histogram of Oriented Gradient *

Abstract

Spices are biological resources that have long played a very important role in everyday life. Spices have characteristics, shapes, and colors that are almost similar and it is difficult to distinguish one spice from another. To assist in recognizing the characteristics of existing spices, the author tries to do research with the title. "Spices Classification Using the K-Nearest Neighbor (K-NN) Method and Using Histogram Oriented Gradient Feature Extraction. The method used in this study is the K-Nearest Neighbor and uses the Histogram Of Oriented Gradient feature extraction. In this study, the dataset used was 2250 image samples and divided into two categories, namely training data and testing data with a ratio of 80%: 20%. The results of this study indicate that the most optimal testing distance formula, namely the Manhattan distance formula, obtained an average accuracy of 87%, 87% precision, 87% recall, 87% f1 score, 87% Fbeta score, and 77% Jaccard score. These results indicate that feature extraction greatly influences the number of types in extracting information, the Histogram of Oriented Gradient works optimally when the number of types extracted is small and not optimal when used in a large number of classification types.