Proposed Rice Leaf Diseases Classification Model Based on the pre-trained VGG-16 Model with Transfer Learning Technique

• Author(s): Lai Yee Win Lwin
• Paper ID: 1706312
• Page: 407-413
• Published Date: 24-09-2024
• Published In: Iconic Research And Engineering Journals
• Publisher: IRE Journals
• e-ISSN: 2456-8880
• Volume/Issue: Volume 8 Issue 3 September-2024

Abstract

Given the widespread consumption of rice across numerous countries, it stands as one of the most extensively cultivated crops globally. To achieve successful rice cultivation , it is essential to comprehend the different stages involved in the process and to be aware of the various disease that can affect the crop introduced a researchers have introduced a range of diagnostic techniques specifically for rice. Among the various diagnostic methods, one notable approach is the classification method utilizing deep learning. This method employs convolutional neural network architectures to automatically classify diseases by analyzing images of rice leaves collected from rice fields. This paper employs the VGG-16 models, which has been pre-trained, to classify various types of leaf diseases in rice plants utilizing the Transfer Learning approach. In this system, Dataset containing diseased rice leaf images are used to distinguish disease types. The proposed model and VGG-16 model have been used as baseline models on the dataset and result have been analyzed. In the evaluation part, the performance of the models is shown using testing datasets.

Keywords

Classification, Deep learning, Convolutional Neural Networks (CNN), VGG-16 model

Citations

IRE Journals:
Lai Yee Win Lwin "Proposed Rice Leaf Diseases Classification Model Based on the pre-trained VGG-16 Model with Transfer Learning Technique" Iconic Research And Engineering Journals Volume 8 Issue 3 2024 Page 407-413

IEEE:
Lai Yee Win Lwin "Proposed Rice Leaf Diseases Classification Model Based on the pre-trained VGG-16 Model with Transfer Learning Technique" Iconic Research And Engineering Journals, 8(3)