Lightweight Custom CNNs Take on Corn Leaf Disease: Deep Learning for Plant Pathology

Detecting corn leaf diseases helps farmers identify and treat impacted crops. Early disease identification reduces crop loss. Manual leaf diagnostic imaging takes time and is prone to mistakes. This paper suggests a deep convolutional neural network (DCNN) model for autonomous corn leaf disease identification. Datasets named PlantVillage and PlantDoc are utilized. The dataset contains 4,188 photos of healthy corn leaves and three corn leaf illnesses. The photos have disease labels. The images have been rotated, flipped, and scaled images for augmentation. After augmentation, the dataset contains 12,000 photographs in total. Several pre-trained architectures like InceptionResNetV2, MobileNetV2, ResNet50, VGG19, InceptionV3, VGG16, and DenseNet201 have been chosen for their image feature extraction and large dataset learning capabilities. Furthermore, this paper proposes a custom CNN model which is lightweight compared to those pre-trained models. Our proposed CNN model achieves 99.56% accuracy in case of training dataset and 98.42% for the validation dataset. The model accurately detects corn leaf diseases in new photos. The model is computationally light, making it suited for smartphones and drones. A maize leaf disease detection mobile app has been created using the proposed CNN model. The application can detect corn leaves uploaded by anyone. An API analyzes an image using our proposed model from the device’s camera or gallery when a user selects it and produces accurate prediction.