Deep Neural Network for Multi-Classification of Parsley Leaf Spot Disease Detection

Plant disease recognition and classification has been an active area of research based on computer vision techniques. Herb disease detection has been lacking due to a large amount of study focusing on plant diseases as herbs are also part of the plant family and very much prone to diseases. A parsley leaf disease detection and classification model has been developed to diagnose and differentiate parsley leaf spot (PLS) disease according to the disease severity. The proposed model is a convolutional neural network (CNN) based deep learning (DL) model to classify 2000 real-phase images dataset of parsley leaf containing healthy and PLS infected images, resulting in 99.5% classification accuracy in case of both binary and multi-classification of the PLS disease. In addition to this, the proposed model has also been compared with state-of-the-art pre-trained models which show the out-performance of the proposed model in terms of multi-classification of PLS disease.