Novila, Aan Nura (2026) KLASIFIKASI PENYAKIT DAUN TOMAT BERDASARKAN CITRA DIGITAL MENGGUNAKAN NAIVE BAYES. Other thesis, Universitas Nurul Jadid.
![[thumbnail of TA AAN_watermark.pdf]](https://repository.unuja.ac.id/style/images/fileicons/text.png) |
Text
TA AAN_watermark.pdf Restricted to Registered users only Download (41MB) | Request a copy |
Abstract
Tomato leaf diseases are one of the factors that can reduce crop quality and productivity.
Manual disease identification often requires considerable time and depends on the
observer's experience, making it necessary to develop a system that can assist the
identification process more quickly and accurately. This study aims to develop a digital
image-based tomato leaf disease classification system using the Gaussian Naive Bayes
algorithm combined with Hue, Saturation, Value (HSV) and Gray Level Co-occurrence
Matrix (GLCM) feature extraction methods. The dataset consisted of 300 images belonging
to three classes: Bacterial Spot, Healthy, and Yellow Leaf Curl. The research stages
included image preprocessing, color feature extraction using HSV, texture feature
extraction using GLCM, data splitting with a ratio of 80% for training data and 20% for
testing data, model training using the Gaussian Naive Bayes algorithm, and model
performance evaluation using accuracy, precision, recall, and F1-score. In addition, User
Acceptance Testing (UAT) was conducted to evaluate user acceptance of the developed
application. The experimental results showed that the proposed model achieved an
accuracy of 91.67%, indicating that it was capable of classifying tomato leaf diseases
effectively based on the extracted color and texture features. Furthermore, the UAT
evaluation obtained a score of 84.25%, which falls into the Very Good category, indicating
that the application is easy to use, provides a clear interface, and effectively assists users in
identifying tomato leaf diseases. Therefore, the combination of HSV and GLCM feature
extraction with the Gaussian Naive Bayes algorithm can be applied as an effective approach
for digital image-based tomato leaf disease classification.
| Item Type: | Thesis (Other) |
|---|---|
| Uncontrolled Keywords: | Tomato Leaf Disease, Gaussian Naive Bayes, HSV, GLCM, Classification. |
| Subjects: | Q Science > Q Science (General) S Agriculture > SB Plant culture T Technology > T Technology (General) |
| Divisions: | Fakultas Teknik > S1 Teknik Informatika |
| Depositing User: | Unnamed user with email [email protected] |
| Date Deposited: | 30 Oct 2026 00:20 |
| Last Modified: | 30 Oct 2026 00:20 |
| URI: | https://repository.unuja.ac.id/id/eprint/5603 |
Actions (login required)
 |
View Item |