A Hybrid Model for the Classification of Sunflower Diseases Using Deep Learning
Akash Sirohi, Arun Malik
Abstract
Prediction and Recognition of plant disease in the early stage is one of the most essential needs to increase agriculture, which plays an important role in our country's economy and helps to feed a large population. And with the help of earlier detection, we can save the plants and avoid losses. Deep learning techniques are used widely to classify or predict diseases by using images. This paper proposed a hybrid model of deep learning to classify the sunflower diseases, i.e. Alternaria leaf blight, Downy mildew, Phoma blight, and Verticillium wilt. To make a hybrid model I used the stacking ensemble learning technique and combine two models i.e. VGG-16 and MobileNet, We also make our own dataset with Google images, and our proposed model gave 89.2% accuracy on our dataset, which is better than the other models.