Aminatus Syarifah
Muria Kudus University

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

KLASIFIKASI TINGKAT KEMATANGAN JAMBU BOL BERBASIS PENGOLAHAN CITRA DIGITAL MENGGUNAKAN METODE K-NEAREST NEIGHBOR Aminatus Syarifah; Aditya Akbar Riadi; Arief Susanto
J I M P - Jurnal Informatika Merdeka Pasuruan Vol 7, No 1 (2022): MARET
Publisher : Fakultas Teknologi Informasi Universitas Merdeka Pasuruan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37438/jimp.v7i1.417

Abstract

Guava (Syzygium Malacence) is a type of water guava plant that has white flesh color, elliptical fruit shape, red to purplish skin color, and has one brown seed in each fruit. There are 2 types of guava, namely white guava, and red guava. In this study, the object of research is the type of red guava. The red guavas that are traded in traditional markets and fruit shops have different levels of ripeness. Farmers and traders do sorting to distinguish types of guava bol based on the level of maturity manually using eyes/visuals. The existence of increasingly advanced technological developments can make it easier for farmers and traders in sorting red guava fruit by using a classification application based on digital image processing. The classification process is divided into 3 types, namely raw, ripe, and very ripe/old. This research uses HSV (Hue Saturation Value) color feature extraction and GLCM (Gray Level Co-Occurrence Matrix)  feature extraction methods. Meanwhile, the classification method uses the K-NN (K-Nearest Neighbor) method. The guava data used is 90 data consisting of 60 training data and 30 testing data. The results of the classification using the K-NN method in the application have an accuracy rate of 93% from 30 testing data. The accuracy is obtained with the neighboring value used as k=1.Keywords— Guava, Digital Image Processing, K-NN, Extraction, HSV, GLCM