Plant Disease Classification using Fine-grained Techniques
| dc.contributor.author | BLIZAK, Widad | |
| dc.contributor.author | BOUDJOUDI, Ferial Amina | |
| dc.contributor.author | DEBBI, Hichem: Superviser | |
| dc.date.accessioned | 2024-07-02T11:02:05Z | |
| dc.date.available | 2024-07-02T11:02:05Z | |
| dc.date.issued | 2024-06 | |
| dc.description.abstract | Plant diseases significantly impact agricultural productivity and global food security. This study aims to develop a precise model for classifying plant leaf diseases using fine-grained techniques involving deep learning and computer vision. Focusing on three different datasets—tomato, grape, and watermelon leaves, which are among the most consumed and produced fruits in Algeria—we employed the VGG19 convolutional neural network (CNN) to analyze and accurately classify images of diseased and healthy leaves. The model demonstrated high accuracy and robustness, which were further validated through various performance metrics. A practical application was also developed to facilitate real-time disease diagnosis, aiding farmers in effective crop management and enhancing food security. | |
| dc.identifier.uri | https://dspace.univ-msila.dz/handle/123456789/43051 | |
| dc.language.iso | en | |
| dc.publisher | UNIVERSITY MOHAMED BOUDIAF- MSILA, FACULTY OF MATHEMATICS AND INFORMATICS, DEPARTMENT OF COMPUTER SCIENCE | |
| dc.subject | Plant disease classification | |
| dc.subject | deep learning | |
| dc.subject | VGG19 | |
| dc.subject | computer vision | |
| dc.subject | food security | |
| dc.subject | mobile application | |
| dc.subject | precision agriculture | |
| dc.title | Plant Disease Classification using Fine-grained Techniques | |
| dc.type | Thesis |