IoT-Based Blight Severity Disease Recognition System in Tomato Plant

• Published in: 2024 Second International Conference on Emerging Trends in Information Technology and Engineering (ICETITE) pp. 1 - 5
• Main Authors: Coumar, S. Oudaya, Rathnam, Z. Mani, Vinay, K., Bhargav, G. Sai
• Format: Conference Proceeding
• Language: English
• Published: IEEE 22.02.2024
• Subjects: Agriculture; CNN; Deep learning; Food security; Machine learning; Plants (biology); Real-time systems; Sensors; Transforms
• DOI: 10.1109/ic-ETITE58242.2024.10493839

Tomato plant which is scientifically called as Solanum lycopersicum, they are very important in global agriculture as food source. However, they are much known to blight diseases that they can severely impact on crop yields. These blight diseases are two types namely Early blight and Late blight. The accurate identification of blight disease is necessary for effective disease management and ensuring food security through the integration of machine learning. This paper presents an IoT system that incorporates several sensors to monitor environmental parameters, including accuracy and validation in real-time. These datasets are used to create a responsive and dynamic monitoring network for tomato plants. The high-resolution images of tomato leaves are captured by using enabled cameras. By taking help of Machine learning techniques like convolution neural networks (CNNs) and deep learning we can able to analyze the leaf images and identify early and late blight symptoms. The machine learning model provides the remarkable accuracy in between healthy leaves and those affected by blight and also categorize the level of the disease.