9th International Conference on ICT for Sustainable Development

Authors - Priyanka Patel, Anshuman Prajapati, Viraj Koradia
Abstract - One of the most significant fruit crops in the world is the mango, however mango illnesses can significantly reduce crop productivity and quality, which has an effect on the industry's profitability. It is difficult to identify mango illnesses at an early stage because conventional ways for doing so require a lot of time and labor. In this study, we developed a unique method for applying deep learning to identify mango disease leaf. model approach consists of four steps: collection, data preprocessing, model training, and model evaluation. A collection of 1000-1200 photos of mango leaves, both healthy and sick, was gathered. The photographs were pre-processed using methods like pixel normalization, color correction, and image scaling. Metrics including accuracy, precision, recall, and F1-score were then used to evaluate the convolutional neural network (CNN) model's performance. This method's accuracy on the testing set was 90-95%, demonstrating its potency in identifying mango illnesses. By reducing the losses caused by mango diseases, the recommended method would improve the efficacy and precision of mango disease diagnostics, which would be beneficial to the fruit industry.