Kombinasi Metode Ekstraksi Fitur dan Metode Klasifikasi untuk Identifikasi Penyakit pada Citra Daun Kentang

Wardhani, Gusti Ayu Ardell Salsa (2025) Kombinasi Metode Ekstraksi Fitur dan Metode Klasifikasi untuk Identifikasi Penyakit pada Citra Daun Kentang. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 06111940000062-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 April 2027. Download (4MB) | Request a copy

Abstract

Kentang merupakan salah satu tanaman pangan utama di seluruh dunia yang penting secara ekonomi dan gizi, namun rentan terhadap berbagai penyakit yang dapat menurunkan produktivitasnya. Penelitian ini melakukan kombinasi metode ekstraksi fitur dan klasifikasi untuk identifikasi penyakit pada citra daun kentang. Tiga metode ekstraksi fitur yang digunakan adalah Gray Level Co-Occurrence Matrix (GLCM), Histogram of Oriented Gradients (HOG), dan Local Binary Patterns (LBP). Sementara itu, metode klasifikasi yang diterapkan meliputi Support Vector Machine (SVM), Random Forest dan Adaptive Neuro Fuzzy Inference System (ANFIS). Dataset citra daun kentang yang digunakan terdiri dari tiga kategori: sehat (healthy), hawar daun atau busuk daun (late blight), dan bercak kering daun (early blight). Penelitian ini bertujuan untuk mengevaluasi efektivitas kombinasi metode ekstraksi fitur dan klasifikasi dalam mengidentifikasi penyakit pada daun kentang. Pada penelitian tugas akhir ini dilakukan kombinasi metode ekstraksi fitur Gray Level Co-Occurrence Matrix (GLCM), Histogram of Oriented Gradients (HOG), dan Local Binary Patterns (LBP) dan klasifikasi Support Vector Machine (SVM), Random Forest dan Adaptive Neuro Fuzzy Inference System (ANFIS) untuk identifikasi penyakit pada citra daun kentang. Hasil kombinasi metode ekstraksi fitur dan klasifikasi terbaik telah diperoleh menggunakan metode LBP yang dikombinasikan dengan SVM dengan rata-rata akurasi sebesar 88.78%.
==============================================================================================================================
Potato is one of the major food crops worldwide that is economically and nutritionally important, but is susceptible to various diseases that can reduce its productivity. This study combines feature extraction and classification methods for disease identification in potato leaf images. The three feature extraction methods used are Gray Level Co-Occurrence Matrix (GLCM), Histogram of Oriented Gradients (HOG), and Local Binary Patterns (LBP). Meanwhile, the classification methods applied include Support Vector Machine (SVM), Random Forest and Adaptive Neuro Fuzzy Inference System (ANFIS). The potato leaf image dataset used consists of three categories: healthy, late blight, and early blight. This research aims to evaluate the effectiveness of a combination of feature extraction and classification methods in identifying diseases in potato leaves. In this final project research, a combination of Gray Level Co-Occurrence Matrix (GLCM), Histogram of Oriented Gradients (HOG), and Local Binary Patterns (LBP) feature extraction methods and Support Vector Machine (SVM), Random Forest and Adaptive Neuro Fuzzy Inference System (ANFIS) classifications are carried out for disease identification in potato leaf images. The best combination of feature extraction and classification methods has been obtained using the LBP method combined with SVM with an average accuracy of 88.78%

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Ekstraksi fitur, klasifikasi, daun kentang, GLCM, HOG, LBP, SVM, ANFIS, Random Forest, Feature extraction, classification, potato leaf
Subjects:	Q Science > Q Science (General) > Q325.5 Machine learning. Support vector machines.
Divisions:	Faculty of Science and Data Analytics (SCIENTICS) > Mathematics > 44201-(S1) Undergraduate Thesis
Depositing User:	Wardhani Gusti Ayu Ardell Salsa
Date Deposited:	03 Feb 2025 12:52
Last Modified:	03 Feb 2025 12:52
URI:	http://repository.its.ac.id/id/eprint/117915

Actions (login required)

View Item