Claim Missing Document

Found 1 Documents
Journal : SMATIKA

Klasifikasi Bumbu Dapur Indonesia Menggunakan Metode K-Nearest Neighbors (K-NN) Suastika Yulia Riska; Lia Farokhah
SMATIKA JURNAL Vol 11 No 01 (2021): SMATIKA Jurnal : STIKI Informatika Jurnal

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32664/smatika.v11i01.568


Seasoning is one of the most important elements in a dish. Indonesian herbs or spices have a very wide variety of types. Mistakes in choosing spices have a big effect on the taste of the dish. Image processing is a branch of science in the field of technology that can be used to recognize image objeks captured by the camera. This study will classify the types of spices that are almost similar, namely ginger, galangal, turmeric and kencur. The classification method used is K-Nearest Neighbor (K-NN). In this study we tested how to split training data and data testing, namely 66.7%: 33.33%, 75%: 25% and 90%: 10%. The sharing of training data and testing data uses 90%: 10% has the greatest average accuracy compared to other distribution methods. The selection of K = 3 or K = 5 has an average accuracy that is almost the same in all methods of split training data and testing data, namely 64.66%: 65%. At K = 1 it has a fairly high accuracy compared to the previous K, which is 73%.