Please use this identifier to cite or link to this item:
https://repositori.uma.ac.id/handle/123456789/28109
Title: | Klasifikasi Penyakit Cabai Merah Melalui Citra Daun dengan Pemanfaatan Model Vgg19 |
Other Titles: | Classification of Red Chili Diseases Through Leaf Images Using the Vgg19 Model |
Authors: | Sinaga, Lewisa Malihi Putra |
metadata.dc.contributor.advisor: | Muhathir |
Keywords: | Klasifikasi;Penyakit Cabai Merah;Citra Daun;VGG19;CNN;Red Chili Disease |
Issue Date: | 12-Mar-2025 |
Publisher: | Universitas Medan Area |
Series/Report no.: | NPM;198160023 |
Abstract: | Penyakit pada tanaman cabai merah merupakan salah satu permasalahan serius dalam sektor pertanian yang dapat menyebabkan penurunan produktivitas secara signifikan. Dalam beberapa tahun terakhir, sistem berbasis kecerdasan buatan, khususnya Convolutional Neural Network (CNN), telah banyak diaplikasikan untuk deteksi penyakit tanaman secara otomatis dan akurat. Penelitian ini bertujuan untuk mengevaluasi efektivitas model CNN dengan arsitektur VGG19 dalam mengklasifikasikan penyakit pada daun cabai merah berbasis citra visual. Metodologi penelitian meliputi tahapan prapemrosesan citra, ekstraksi fitur, dan pelatihan model VGG19 menggunakan dataset citra daun cabai merah yang terdiri dari citra daun sehat dan terinfeksi penyakit. Hasil penelitian menunjukkan bahwa implementasi CNN dengan arsitektur VGG19 menghasilkan performa klasifikasi penyakit daun cabai merah yang sangat baik. Dengan hyperparameter optimal meliputi epoch 20, optimizer RMSprop, dan learning rate 0.001, model mencapai akurasi 0.9833, presisi 0.9841, recall 0.9833, dan F1-score 0.9833. penelitian ini efektif digunakan untuk deteksi otomatis penyakit pada tanaman cabai merah, serta berpotensi menjadi landasan untuk pengembangan sistem pemantauan (monitoring). Untuk penelitian selanjutnya, disarankan melakukan eksplorasi terhadap arsitektur CNN lain, pengembangan aplikasi mobile berbasis Android, atau integrasi teknologi drone untuk akuisisi citra secara real-time guna mendukung sistem monitoring. Red chili plant diseases are a serious problem in the agricultural sector, causing significant productivity losses. In recent years, artificial intelligence-based systems, particularly Convolutional Neural Networks (CNNs), have been widely applied for automatic and accurate plant disease detection. This study aims to evaluate the effectiveness of a CNN model with the VGG19 architecture in classifying red chili leaf diseases based on visual imagery. The research methodology included image preprocessing, feature extraction, and training the VGG19 model using a red chili leaf image dataset consisting of healthy and diseased leaves. The results showed that the implementation of the CNN with the VGG19 architecture produced excellent classification performance for red chili leaf diseases. With optimal hyperparameters of 20 epochs, an RMSprop optimizer, and a learning rate of 0.001, the model achieved an accuracy of 0.9833, a precision of 0.9841, a recall of 0.9833, and an F1-score of 0.9833. This research is effective for automatic disease detection in red chili plants and has the potential to serve as a foundation for developing a monitoring system. For further research, it is recommended to explore other CNN architectures, develop Android-based mobile applications, or integrate drone technology for real-time image acquisition to support monitoring systems. |
Description: | 62 Halaman |
URI: | https://repositori.uma.ac.id/handle/123456789/28109 |
Appears in Collections: | SP - Informatic Engineering |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
198160023 - Lewisa Malihi Putra Sinaga - Chapter IV.pdf Restricted Access | Chapter IV | 1.57 MB | Adobe PDF | View/Open Request a copy |
198160023 - Lewisa Malihi Putra Sinaga - Fulltext.pdf | Cover, Abstract, Chapter I, II, III, V, Bibliography | 2.21 MB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.