Detection of Apple Plant Diseases Using Leaf Images Through Convolutional Neural Network

Plant diseases are a severe cause of crop losses in the agriculture globally. Detection plants is difficult and challenging due to lack expert knowledge. Deep learning-based models provide promising ways identify plant using leaf images. However, need larger training sets, computational complexity, overfitting, etc. major issues with these techniques that still be addressed. In this work, convolutional neural network (CNN) developed consists smaller number layers leading lower burden. Some augmentation such as shift, shear, scaling, zoom, flipping applied generate additional samples increasing set without actually capturing more The CNN model trained for apple publicly available dataset PlantVillage Scab, Black rot, Cedar rust leaves. rigorous experimental results revealed proposed well fit achieves 98% classification accuracy. It also evident from it needs lesser amount storage takes execution time than several existing deep models. Although, there exist disease detection comparable accuracy, but resources. Therefore, highly suitable deploying handheld devices.