Multi-Level Deep Learning Model for Potato Leaf Disease Recognition

Potato leaf disease detection in an early stage is challenging because of variations crop species, diseases symptoms and environmental factors. These factors make it difficult to detect potato the stage. Various machine learning techniques have been developed diseases. However, existing methods cannot species general these models are trained tested on images plant leaves a specific region. In this research, multi-level deep model for recognition has developed. At first level, extracts from image using YOLOv5 segmentation technique. second novel technique convolutional neural network blight late images. The proposed was dataset. dataset contains 4062 collected Central Punjab region Pakistan. achieved 99.75% accuracy performance also evaluated PlantVillage compared with state-of-the-art significantly concerning computational cost.