FUSI FITUR GABOR DAN COLOR MOMENT HSV UNTUK KLASIFIKASI CITRA PENYAKIT TANAMAN PADI MENGGUNAKAN SUPPORT VECTOR MACHINE

Husnul Khatimah, NIM.: 22106050015 (2026) FUSI FITUR GABOR DAN COLOR MOMENT HSV UNTUK KLASIFIKASI CITRA PENYAKIT TANAMAN PADI MENGGUNAKAN SUPPORT VECTOR MACHINE. Skripsi thesis, UIN SUNAN KALIJAGA YOGYAKARTA.

Preview	Text (FUSI FITUR GABOR DAN COLOR MOMENT HSV UNTUK KLASIFIKASI CITRA PENYAKIT TANAMAN PADI MENGGUNAKAN SUPPORT VECTOR MACHINE) 22106050015_BAB-I_IV-atau-V_DAFTAR-PUSTAKA.pdf - Published Version Download (5MB) | Preview
	Text (FUSI FITUR GABOR DAN COLOR MOMENT HSV UNTUK KLASIFIKASI CITRA PENYAKIT TANAMAN PADI MENGGUNAKAN SUPPORT VECTOR MACHINE) 22106050015_BAB-II_sampai_SEBELUM-BAB-TERAKHIR.pdf - Published Version Restricted to Registered users only Download (10MB) | Request a copy

Abstract

Rice productivity has declined due to the difficulty of accurately identifying leaf diseases because of the similarity of symptoms and the limitations of visual observation. To improve the classification process, this study applies Gabor and HSV Color Moment feature fusion using a Support Vector Machine. The dataset used is from Kaggle and includes six disease classes. Gabor is used to extract texture information based on a combination of frequency and orientation, while Color Moment HSV is used to extract color information through the Hue, Saturation, and Value channels. These two features are combined using concatenation and serve as input for the SVM model. Evaluation was conducted using accuracy, precision, recall, F1-score, confusion matrix, and 5-fold K-Fold Cross Validation. The research results show that the Fusion feature (Gabor+HSV) provides better classification performance compared to single features. In the initial testing, the Fusion feature achieved an accuracy of 0.93, higher than the Gabor feature at 0.85 and the HSV feature at 0.82. After hyperparameter tuning, the accuracy of the Fusion feature increased to 0.94 with an average K-Fold Cross Validation accuracy of 0.933. These results indicate that combining texture and color features enhances the model’s ability to distinguish between each class of rice leaf diseases.

Share this knowledge with your friends :

Actions (login required)

View Item