enhancing agricultural diagnostics: tomato leaf disease detection using quantum vision transformer

The early and accurate detection of plant diseases is vital for ensuring food security and enhancing agricultural productivity. tomato plants, being one of the most widely cultivated crops, are particularly susceptible to several prevalent leaf conditions. these conditions can lead to significant crop losses and adversely affect both yield and quality, posing a substantial challenge to farmers and the agricultural industry. to identify tomato leaf conditions, traditional methods such as machine learning and modern approaches like various deep learning architectures have been developed and studied by researchers. this paper presents a novel approach for the detection of ten classes of tomato leaf conditions, encompassing both healthy and diseased leaves. the proposed method leverages a new quantum vision transformer architecture, integrating variational quantum circuits within both the attention mechanism and the multi-layer perceptron. in our study, we conducted extensive experiments comparing the performance of the quantum vision transformer with the vision transformer. the experimental results demonstrate that the quantum vision transformer model achieves an area under the curve of 0.928 and an accuracy of 66.85%, while the vision transformer model reaches an area under the curve of 0.95 and an accuracy of 72.15%. this highlights the effectiveness and robustness of both models in accurately detecting tomato leaf conditions. the research findings suggest that the quantum vision transformer architecture can serve as a powerful tool for early detection in agricultural applications using quantum computers, contributing to more efficient and sustainable farming practices.