Enhancing plant disease detection: a novel CNN-based approach with tensor subspace learning and HOWSVD-MDA

Machine learning has revolutionized the field of agricultural science, particularly in the early detection and management of plant diseases, which are crucial for maintaining crop health and productivity. Leveraging advanced algorithms and imaging technologies, researchers are now able to identify and classify plant diseases with unprecedented accuracy and speed. Effective management of tomato diseases is crucial for enhancing agricultural productivity. The development and application of tomato disease classification methods are central to this objective. This paper introduces a cutting-edge technique for the detection and classification of tomato leaf diseases, utilizing insights from the latest pre-trained convolutional neural network (CNN) models. We propose a sophisticated approach within the domain of tensor subspace learning, known as higher-order whitened singular value decomposition (HOWSVD), designed to boost the discriminatory power of the system. Our approach to tensor subspace learning is methodically executed in two phases, beginning with HOWSVD and culminating in multilinear discriminant analysis (MDA). The novelty of this study lies in the integration of HOWSVD and MDA, enhancing the discriminatory capabilities of high-dimensional CNN embeddings. Our HOWSVD method preprocesses and reduces the high dimensionality of features while preserving crucial variance. Subsequently, the application of MDA ensures the maximization of class separability within the transformed tensor subspace. Our results demonstrate that HOWSVD-MDA achieves superior accuracy compared to existing methods. The efficacy of this innovative method was rigorously tested through comprehensive experiments on two distinct datasets, namely, PlantVillage and the Taiwan dataset. Key findings include achieving up to 98.36% accuracy on the PlantVillage dataset and 98.39% on the Taiwan dataset, significantly outperforming current state-of-the-art techniques. The findings reveal that HOWSVD-MDA outperforms existing methods, underscoring its capability to markedly enhance the precision and dependability of diagnosing tomato leaf diseases.