PROBLEM STATEMENT
Crop devastation due to plant diseases poses a critical threat to global food security. Pathogens, such as fungi, bacteria, and viruses, target essential crops, leading to yield losses, economic hardship for farmers, and potential famine. The lack of effective and sustainable disease management strategies exacerbates the problem, jeopardizing agricultural systems. Urgent research is needed to identify resistant crop varieties, develop environmentally friendly control measures, and enhance farmers' knowledge for early detection and prevention. Addressing this issue is paramount for ensuring a stable and sufficient food supply to meet the demands of a growing population and mitigate the impact of plant diseases on global agriculture.
OBJECTIVE
- Achieve precise classification of images from the testing dataset, distinguishing between various disease categories or a healthy leaf.
- Enable accurate identification and differentiation of multiple diseases, even when presented on a single leaf.
- Enhance the model's capability to handle rare classes and novel symptoms for comprehensive disease coverage.
- Ensure user-friendly interfaces to empower farmers in interpreting and acting upon diagnostic results efficiently.
DATASET USED
The dataset of Disease Detection in Plants have been taken to train the model from Kaggle.
PYTHON LIBRARIES USED
- OpenCV
- Numpy
- Pandas
- Keras
- Matplotlib
- Scikit-Learn