Plant Disease Detection using Resampling Cubature Kalman Filter and Focused Transformer with Quantum Fuzzy Cell Attention Networks

Major obstacles to plant leaf disease diagnosis are uneven illumination, similar sickness symptoms, unbalanced data, expensive processing, and early infection detection difficulties. Model accuracy, reliability, and generalization among various plant types are also affected by environmental factors, occlusions, and image noise. The performance of the Resampling Cubature Kalman Filter and Focused Transformer with Quantum Fuzzy Cell Attention Networks (RCKF-FT-QFCANet) is verified against the PlantVillage dataset for plant disease detection. Step one involves the Resampling Cubature Kalman Filter (RCKF) enhancing image quality. Leaf regions were affected by the Geometric Algebra Transformer (GAT) segments based on varying regions. The classifier, Focused Transformer with Quantum Fuzzy Cell Attention Networks (FT-QFCANet), features and classifies diseases. The Wall Construction Algorithm (WCA) improves categorization accuracy by looking at various affected leaf areas. The Python test script employs the PlantVillage dataset, with findings indicating that RCKF-FT-QFCANet performs better than existing methods with 99.9% efficiency and 99.8% sensitivity, showing the potential of computer systems for replacing manual diagnosis.