Affiliation: Computer Science and Engineering, Graphic Era Hill University, Dehradun, India
Abstract: This research addresses the urgent need for sophisticated and effective tomato plant disease detection methods in India's agricultural landscape. Tomatoes, a crucial crop for culinary richness and economic sustenance, face formidable challenges from bacterial, fungal, and viral infections. Existing detection methods rely on image processing and machine learning, yet limitations persist in terms of accuracy, generalization, and real-time applicability. This paper proposes a novel Tomato Plant Disease Predictor comprising a feature extractor and classifier integrating real-time imaging and a fine-tuned Convolutional Neural Network (CNN). The methodology aims to overcome current shortcomings and enhance precision, applicability, and generalization. The findings promise to benefit farmers by revolutionizing agricultural practices, lessening workloads, and promoting sustainable solutions.
Keywords: Tomato disease detection, real-time cameras, computer vision, machine learning, image processing.
Introduction: The document introduces the significance of tomatoes in India's agrarian economy and the challenges posed by various diseases affecting tomato crops. It emphasizes the necessity for advanced and automated detection systems to mitigate these challenges.
Methodology: The proposed model uses real-time imaging and a fine-tuned CNN to improve tomato plant disease detection. The dataset includes various diseased and healthy tomato leaf images. The model incorporates feature extraction, image preprocessing, and machine learning techniques to achieve high accuracy in disease detection.
Results and Discussion: The document discusses the performance of the proposed model in detecting tomato plant diseases, highlighting improvements over existing methods. It includes a comparison with other models and addresses issues related to dataset size, generalization, and real-time applicability.
Conclusion: The study presents a robust approach using cutting-edge technologies, marking a significant step towards proactive and precise crop disease management. The research has the potential to enhance agricultural productivity, reduce the need for chemical interventions, and promote sustainable farming practices.