Corn is one of the most important carbohydrate-producing food crops in Indonesia besides rice and wheat. Every year Indonesia can produce a very large amount of corn. It is proven that in 2017 Indonesia can produce 22.59 million tons of corn. This number is very meaningful for the economy in Indonesia. One of the most widely grown corns in Indonesia is pearl corn. However, it is quite difficult to distinguish each variety of corn because the shape and color tend to be the same. One way to find out a corn variety is by utilizing the image processing data for each corn. One of the classification methods used is K-NN. Each corn image is taken the value of area, parimeter, width, length, metric and eccentricity using the Matlab application to determine the shape of a corn, then 250 data are collected. The data that has been collected is divided based on a ratio of 70% training data 30% test data and applying k values, namely 3, 5 and 7. The classification process uses the cloud-based Rstudio application. The results obtained, it is known that the test at k = 3 gets the highest accuracy value compared to other k values. The accuracy obtained is 93.24% followed by recall 91.89% precision 94.44% specificity 94.59% error rate 6.76% and f-measure 0.9315.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.