Abstract:
The automatic detection of diseases in plants is necessary, as it reduces the tedious work of
monitoring large farms and it will detect the disease at an early stage of its occurrence to minimize
further degradation of plants. Besides the decline of plant health, a country’s economy is highly
affected by this scenario due to lower production. The current approach to identify diseases by an
expert is slow and non-optimal for large farms. Our proposed model is an ensemble of pre-trained
DenseNet121, EfficientNetB7, and EfficientNet NoisyStudent, which aims to classify leaves of apple
trees into one of the following categories: healthy, apple scab, apple cedar rust, and multiple diseases,
using its images. Various Image Augmentation techniques are included in this research to increase the
dataset size, and subsequentially, the model’s accuracy increases. Our proposed model achieves an
accuracy of 96.25% on the validation dataset. The proposed model can identify leaves with multiple
diseases with 90% accuracy. Our proposed model achieved a good performance on different metrics
and can be deployed in the agricultural domain to identify plant health accurately and timely.
