Please use this identifier to cite or link to this item:
https://repositori.uma.ac.id/handle/123456789/22741
Title: | Implementasi Algoritma K-Nearest Neighbor Dalam Klasifikasi Jamur Pada Citra Roti Tawarmenggunakan Ekstraksi Fitur ORB |
Other Titles: | Implementation of the K-Nearest Neighbor Algorithm In Classification of Fungi on Bread Images Bargaining using Extraction ORB Features |
Authors: | Br Munthe, Santi |
metadata.dc.contributor.advisor: | Muliono, Rizki Muhathir |
Keywords: | White Bre;KNN;ORB;Roti Tawar |
Issue Date: | 14-Sep-2023 |
Publisher: | Universitas Medan Area |
Series/Report no.: | NPM;178160057 |
Abstract: | Roti tawar adalah pangan yang populer di Indonesia karena rasa enaknya dan harga yang terjangkau. Namun, roti tawar memiliki masalah umur simpan yang relatif pendek karena rentan terhadap pertumbuhan jamur. Pertumbuhan jamur dapat mengubah kualitas roti tawar, membuatnya tidak enak, keras, bahkan tengik. Berdasarkan keunikan pola kerusakan pada roti tawar yang disebabkan oleh jamur, penelitian ini menguji klasifikasi jamur pada citra roti tawar dengan menggunakan algoritma machine learning yaitu KNN (K-Nearest Neighbor) dan memanfaatkan ekstraksi fitur ORB (Oriented FAST and Rotated BRIEF). Tujuan dari penelitian ini adalah untuk mengetahui apakah metode klasifikasi K-Nearest Neighbor dapat berhasil mendeteksi jamur pada citra roti tawar dengan menggunakan ekstraksi fitur ORB (Oriented FAST and Rotated BRIEF). Tingkat akurasi yang dihasilkan oleh metode K-Nearest Neighbor adalah 99%. Yaitu pada roti jamur rendah memiliki Precision 100%, Recall 97%, F1-Score 99%. Roti jamur tinggi memiliki Precision 97%, Recall 100%, F1-Score 99%. Sedangkan roti sehat memiliki Precision 100%, Recall 100%, F1-Score 100% Bread is a popular food in Indonesia due to it’s delicious taste and affordable price. However, bread has a relatively short shelf life as it is susceptible to fungal growth. Leading to issues such as unpleasant taste, hardness, and staleness. Based on the unique pattern of damage caused by mold in bread, this research tests the classification of fungi in images of bread using the K-Nearest Neighbor (KNN) machine learning algorithm and leveraging ORB (Oriented FAST and Rotated BRIEF) feature extraction. The aim of this research is to determine whether the KNearest Neighbor classification method can successfully detect mold in bread images using ORB feature extraction. The accuracy level achieved by the K-Nearest Neighbor method is 99%. Specifically, low mold bread has a Precision of 100%, Recall of 97%, and F1-Score of 99%. High mold bread has a Precision of 97%, Recall 100%, and F1-Score of 99%. Meanwhile, healthy bread has a Precision of 100%, Recall of 100%, and F1-Score of 100%. |
Description: | 65 Halaman |
URI: | https://repositori.uma.ac.id/handle/123456789/22741 |
Appears in Collections: | SP - Informatic Engineering |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
178160057 - Santi Br Munthe - Fulltext.pdf | Cover, Abstract, Chapter I, II, III, V, Bibliography | 2 MB | Adobe PDF | View/Open |
178160057 - Santi Br Munthe - Chapter IV.pdf Restricted Access | Chapter IV | 705.08 kB | Adobe PDF | View/Open Request a copy |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.